Robot hand company settles Tesla trade secret suit and announces $11M raise
The startup, Proception, is taking a unique approach to collecting training data to tackle one of the hardest problems in robotics: hands.
Robotics
86 articles tagged with this keyword, sorted by most recent first.
Comment on Learning Without Simulations? UC Berkeley’s DayDreamer Establishes a Strong Baseline for Real-World Robotic Training by Loren Loore
Always impressed with the depth of your posts. You cover topics thoroughly. www.twohillsseptic.ca
Robotics has a data problem. Macrodata Labs wants to solve it
The AI industry has spent the past several years learning a critical lesson: better data often matters as much as better models. While advances in large language models have been powered by increasing...
AI data infrastructure startup Clairva raises $500K led by Venture Catalysts
AI data infrastructure startup Clairva has raised $500K in a pre-seed funding round led by Venture Catalysts through its angel network. The company will use the fresh capital to strengthen its licensed data supply network, expand partnerships with content owners and institutions, enhance data enrichment and validation capabilities, and support commercial engagement with global AI customers, Clairva said in a press release. Founded in 2025 by Sunil Nair, Sabari Raju, Dushyant Verma, and Amit Parashar, Clairva builds licensed, provenance backed datasets for AI foundation models, embodied AI, robotics, and autonomous systems. As AI models increasingly rely on high quality datasets, sourcing data with clear usage rights, provenance, and cultural context remains a challenge. Clairva works with content owners, production houses, studios, archives, institutions, and contributor networks to source, license, and structure real world data for AI training. The company is initially focused on India, Southeast Asia, and other Global South markets, where languages, environments, behaviours, gestures, workflows, and objects remain underrepresented in AI training datasets. According to Clairva, it is also developing proprietary technology across the data pipeline, including licensed dataset ingestion, rights and provenance tracking, automated enrichment, metadata generation, action and object tagging, temporal segmentation, quality validation, and dataset packaging.
This Humanoid Robot Is a Terrifyingly Competent Office Intern
Flexion Robotics, a startup founded by ex-Nvidia engineers, has a clever way of training robots to do useful work.
AI Weekly Issue #508: The Cutting Edge, Across the Board
One week, the whole frontier. In models, the open weights now run from a 1.6-trillion-parameter behemoth to a 230M model on a Raspberry Pi. In world models and robotics, a startup is training agents on video games to drive real robots and Yann LeCun's team made world models 48× faster. In medicine, GPT-5 Pro cracked a three-year immunology mystery and a founder used Claude to read his own cancer scans. And the agents doing all this reached every phone — and a fresh attack surface. Below: the marquee advances, the deep cuts, and where it's already paying off.
Why China’s tech firms could be in for a rude IPO surprise
A listing path is not a valuation endorsement. China’s artificial intelligence (AI) and robotics companies are about to find out which parts of their private market premiums can survive public market pricing. The Shanghai Stock Exchange has clarified how unprofitable AI large-model companies can apply under the Star Market’s fifth listing standard. The route is meant for companies with strategic technology that might not yet be reaping profits or substantial revenue. A parallel test is taking...
US auto regulators want to kill robotaxi brake pedals
Requiring driverless vehicles to keep human brake controls impedes innovation, the NHTSA says
Robotaxis drive miles just to get cleaned and charged; this new startup wants to fix that
Aseon Labs, which came out of Y Combinator's 2026 spring cohort, has raised $10 million from Crane Venture Partners and others.
Using AI When You Don’t Trust AI
You’ve heard the warnings! Don’t tell ChatGPT your secrets. The robots are reading everything. Your data is the product. And yet here you are: using them as a subscriber. Because AI is genuinely useful! The good news: that distrust is healthy, and you don’t have to choose between using AI and protecting yourself. You can […] The post Using AI When You Don’t Trust AI appeared first on Analytics Vidhya .
How AI is used as a key ingredient at Cosentino
The humble story of Cosentino starts in marble in southeastern Spain in 1945, and subsequent generations have gradually expanded into more diverse materials and color palettes, so now the company operates in more than 120 countries. And what also began in a small factory is now a vast complex exceeding 27 million square feet where machines, cranes, and robots move freely, loading pallets full of product destined for every corner of the globe. Together with partner Microsoft, Cosentino is tackling, like many others, how to most effectively adopt and maximize the potential of AI , and it will be the first industrial company in Spain to adopt the Microsoft Discovery platform. This technology, designed to accelerate scientific research, is particularly interesting to a company whose success is based on the discovery and validation of new materials for kitchens, facades, and interiors. width="1240" height="704" sizes="auto, (max-width: 1240px) 100vw, 1240px"> The Cosentino complex in Almería, Spain. GD | Foundry The research platform developed by Microsoft combines agentic AI, high-performance computing, and advanced KM to accelerate scientific and engineering processes by automating tasks such as literature reviews, hypothesis generation, simulations, and analyses, in order to integrate public and private data into a unified environment for researchers and engineers. For Cosentino, Discovery opens the door to anticipating optimal formulations before production, and reduces the n…
ARX Robotics and Roboneers form ARX Industries to scale unmanned ground vehicle production
German company ARX Robotics and Ukraine's Roboneers today announced the formation of ARX Industries, a joint venture to industrialise the mass production of unmanned ground vehicles. The new entity wi...
Roboflow and Standard Bots Partner to Bring Custom Visual Intelligence to Every Robot
Roboflow and Standard Bots are announcing a partnership to enable robots to see, understand, and act with visual intelligence.
How Loka Built a Natural, Low-Latency Voice Agent with Amazon Nova 2 Sonic
In this post, we demonstrate the architecture and approach Loka used to solve a common frustration: robotic, slow voice assistants that cause customers to hang up, damaging brand reputation and driving up support costs.
I was wary of driverless cars and their tech overlords – but they could give me a different future | Gabriel Stewart
For those of us who can’t drive due to disabilities, the drawbacks of these vehicles are vastly outweighed by the possibilities they offer The robotaxis are coming! The robotaxis are coming! Well, actually, they’re already here. Until now they’ve been the stuff of science fiction, but this summer London’s streets have seen Silicon Valley-based company Waymo testing out self-driving cars. It hasn’t been the smoothest of introductions – from cars getting stuck in a cul-de-sac and repeatedly waking up the residents of Shoreditch to one driving into a crime scene , after a double stabbing in Harlesden. The automated vehicles (AVs) have so far had trained drivers waiting behind the wheel to take control if needed, but will soon be shedding their human minders. Waymo and British rival Wayve are hoping to launch driverless minicabs in the capital this year, subject to approval from the British government and Transport for London, among others. A subsidiary of Google parent Alphabet, Waymo currently operates ride-hailing services in 10 US cities, but London, with its narrow streets and densely populated centre, will serve as one of its biggest challenges yet. Gabriel Stewart is a freelance writer and an intern on the Guardian’s positive action scheme Do you have an opinion on the issues raised in this article? If you would like to submit a response of up to 300 words by email to be considered for publication in our letters section, please click here . Continue reading...
😺 Meta's $299 AI glasses are here
PLUS: Trump's quantum deadline, SpaceX's $6.3B deal, NVIDIA robots
Qdrant Lands in SF: Vector Space Day 2026 Recap
On June 11th, 2026, over 350 developers, researchers, and engineers came together at The Midway in San Francisco for Vector Space Day , our first event of its kind in the United States and our first major gathering in San Francisco. This was a single day, single stage, across three tracks: Agents and Memory, Search and Retrieval, and Edge and Robotics. Hosted by our MC for the day, Adam Chan , who kept the energy flowing from opening keynotes to the final hackathon reveal.
9 ways AI is reshaping enterprise operations: Key insights from AWS Summit NYC
The conversations at last week’s AWS Summit NYC 2026 showed that AI evolution is entering a new phase. From physical robots tackling labor shortages to agentic systems reshaping enterprise operations, the focus is shifting from experimentation to practical deployment. TheCUBE’s host, Gemma Allen, captured candid discussions with Amazon Web Services Inc. executives, partners and customers who are turning […] The post 9 ways AI is reshaping enterprise operations: Key insights from AWS Summit NYC appeared first on SiliconANGLE .
A dexterous soft hand exoskeleton restores intentional grasping in individuals with severe hand impairment
Nature Machine Intelligence, Published online: 23 June 2026; doi:10.1038/s42256-026-01263-3 Nassour, Berberich and colleagues present a soft robotic hand exoskeleton that restores grasping ability in individuals with severe hand paralysis, enabling meaningful tasks such as feeding. A lightweight textile glove with wrist dorsiflexion and an active opposable thumb increases hand articulations to enable more dexterous grasping.
Undergrads’ weed-killing robot wins top prize
A team of Cornell students bested the competition with their invention: an autonomous robot that kills weeds with electricity. The post Undergrads’ weed-killing robot wins top prize appeared first on Cornell AI Initiative .
Building an AI-Powered Robotic Welding Defect Detection System
Use RF-DETR and Gemini 2.5 Pro to identify welding defects and generate automated quality inspection reports.
Eco Wave Power Turns Waves Into Watts With NVIDIA AI Infrastructure and Digital Twins
The next era of AI will not be defined by compute alone. Its growth will be determined by energy. As accelerated computing scales across AI factories, agentic AI, industrial AI, edge computing and physical AI — including robotics and autonomous systems — global electricity demand is rising at unprecedented speed. In many regions, expanding grid […]
Autonomous navigation of intelligent microrobotic swarms in unknown environments
Nature Machine Intelligence, Published online: 22 June 2026; doi:10.1038/s42256-026-01252-6 An, Luo, Zhang and colleagues present Turbo, a transformer-based reinforcement learning framework that enables simulation-to-real transfer for autonomous navigation and obstacle avoidance in physical microrobotic swarms operating in unknown environments.
😼 DeepMind mapped AI agent controls
PLUS: Claude robotics, Dean Ball at OpenAI, DeepSeek's raise, and sovereign models.
IEEE Rolls Out Large Language Models Virtual Training Course
Large language models have moved out of the research lab and into engineers’ daily workflow. LLMs serve as reasoning engines that can orchestrate complex tasks including identifying vulnerabilities in source code and transforming fragmented project discussions into rigorous technical specifications. While the general public uses AI tools to write email and plan vacations, technical professionals use LLMs as core architectural elements that are fundamentally changing how digital infrastructures are built and maintained. As the AI models move into mainstream engineering practice, the demand for technical expertise is rising. The LLM technology market is expected to grow by about 33 percent every year through 2030 , according to MarketsandMarkets . The rapid expansion suggests that proficiency in implementing and securing the models is transitioning from a niche into a core requirement for technologists. More than just a better search engine To use LLMs effectively, technical professionals must move beyond treating them as conversational robots. At a fundamental level, the AI systems are built on the transformer architecture , a framework that replaced the older method of processing data in a fixed, sequential order. Unlike earlier models that analyzed information one step at a time, transformers use self-attention mechanisms to ingest vast datasets simultaneously. For technical professionals, LLMs are core architectural elements that are fundamentally changing how digital infr…
AI coding agents taught robots how to install GPUs and cut zip ties
Nvidia's self-improvement program for robots enlists teams of AI coding agents.
General Motors Is Cutting Its Development Cycles in Half
For decades, automakers enjoyed a luxury that had nothing to do with the softest leather or the smoothest engines. Their luxury was time, with some popular cars and trucks enduring for a decade or longer before they received a full redesign. The clock is ticking faster now, thanks to China. BYD and other automakers there are speeding electric vehicles (EVs) and other models from drawing board to showrooms in two years or less. General Motors is among the Western automakers striving to match that blistering pace, by harnessing AI and simulation to dramatically shorten development times. GM’s effort is being spearheaded by Sterling Anderson , the technologist and robotics guru who led development teams for Tesla’s Autopilot and the Model X before cofounding Aurora Innovation , the autonomous trucking company. GM lured Anderson last June as its chief product officer, offering a US $40 million package to guide the development of the automaker’s cars, autonomous models, batteries, software, and other tech. How GM Is Accelerating Its Designs In a recent video call, Anderson and Jason Fischer , GM’s executive director of virtual integration engineering, walked me through the company’s latest design processes. But first, Anderson offered a wide-lens view of how AI is transforming everything that came before. Sterling Anderson, robotics guru and former Tesla executive, is pushing AI to accelerate GM’s design process. General Motors Anderson sees design and human ingenuity falling int…
😺 Cursor’s $60B SpaceX deal is official
PLUS: Qwen robots, SubQ’s 12M-token model, and more
MolmoMotion: Language-guided 3D motion forecasting
MolmoMotion is an open, language-guided 3D motion forecasting model that predicts how object points will move in the future, enabling stronger motion prediction for robotics, video generation, and other systems that need to reason about what happens next.
Memory at the Edge: On-Device Vector Search with Qdrant Edge
On its first day in an unfamiliar house, a home robot has to build memory as it goes: which rooms it has covered, where it last saw the car keys, whether the kitchen looks different now than it did this morning. And it has to answer those questions itself, where it stands, because the network isn’t always there, and it’s too slow to wait on even when it is. That memory has a concrete shape. As the robot moves, it turns what its camera sees into vectors and writes them to a store it carries onboard. To make a decision, it queries that store for the nearest matches to what it is looking at, filtered by where or when it saw them. Capture, embed, search, decide, and the loop runs entirely on the robot, in milliseconds, with no trip to a server. The engine underneath it is Qdrant Edge : the same Qdrant vector search engine, running in-process as an embedded library instead of behind an API.
Powering Physical AI applications with LeRobot/ROS on Jetson
In this session we will focus on how to bring VLM/VLA models to power real-world physical AI applications. We will focus on how to utilize SOTA of VLM (gemma 4) and or GR00T model for performing different pick and place tasks and orchestrate the outputs to control the robots using ROS 2 framework. You will learn how to bring vision-language models into real-world physical AI applications — from model selection to robot control. We'll cover: Choosing the right model for robotics — learn when to use a state-of-the-art VLM like Gemma 4 versus a specialized model like NVIDIA GR00T, and how runtime, throughput, and task requirements shape that decision. VLMs and VLAs in action — see how vision-language and vision-language-action models are applied to real manipulation tasks like pick and place, and what makes them viable for physical AI. Connecting model outputs to robot control — understand how to orchestrate model outputs through the ROS 2 framework to drive real robot behavior. Hands-on hardware demo — walk through a live example using the SO-101 or reBot Arm, putting everything together from model inference to physical actuation.
Visual Language Models Train Robots to Read Human Emotions
This article is part of our exclusive IEEE Journal Watch series in partnership with IEEE Xplore. As robots advance in terms of dexterity and other physical capabilities , it becomes more likely that humans may find themselves working alongside them. If that happens, how will robots’ emotional capabilities need to advance for them to successfully work with people? In a recent study, researchers trained collaborative robots to read human emotions by not only accounting for facial expressions, but also contextual factors in the interactions as well. Through experiments with 40 volunteers, the researchers then evaluated how a robot’s ability to read human emotions and adjust its behavior in turn impacted a human’s perception of the robot and its capabilities as the two collaborated on tasks. The results —which show that the emotional capabilities of robots only go so far with humans—were published 18 May in IEEE Robotics and Automation Letters . Seung Chan Hong led the study as part of his undergraduate thesis while studying at Monash University, in Melbourne, Australia. He notes that, while there has been a lot of hype in the advancing physical abilities of robots, this is only one piece of the puzzle. “We need to also innovate when it comes to them actually interacting with humans, not just their physical capabilities,” he says. This prompted him to dig deeper into the emotional aspects of human-robot interactions. First, Hong and his co-authors decided to train a robot to rea…
Generate Synthetic Data for Physical AI With NVIDIA Brev Launchables and Agent Skills
Join NVIDIA for a live demonstration of how developers can generate synthetic data for physical AI using NVIDIA Brev Launchables and agent skills. Building synthetic data pipelines for robotics, digital twins, and autonomous systems often requires configuring GPU infrastructure, simulation environments, notebooks, and orchestration tools before meaningful work can begin. In this livestream, we'll show how NVIDIA Brev Launchables and agent skills simplify that process by packaging these components into ready-to-run workflows that help developers move from setup to data generation faster. In this livestream, you'll learn how to: - Launch preconfigured Physical AI development environments - Generate synthetic data using AI-powered workflows - Accelerate robotics, simulation, and digital twin development - Scale from individual tasks to larger synthetic data pipelines - Integrate data generation workflows into broader Physical AI ecosystems Through live, hands-on demonstrations, we'll show how developers can streamline synthetic data creation and reduce the complexity of building Physical AI workflows. Whether you're building robots, training computer vision models, creating digital twins, developing autonomous systems, or exploring Physical AI applications, this session provides a practical introduction to synthetic data generation with NVIDIA Brev Launchables and agent skills. -------------------------------- 📓 Resources Launchable: - Nurec: https://brev.nvidia.com/launchable/…
Can robots read the room?
Artificial intelligence may one day give robots social intelligence, but so far, existing models do a poor job of using human facial cues to predict the outcome of a situation. The post Can robots read the room? appeared first on Cornell AI Initiative .
Breaking down the 2026 Stanford AI Index Report
AI models can win math olympiads… but still struggle to read an analog clock. In this fully connected episode, Dan and Chris break down the latest Stanford AI Index Report and explore what it reveals about the current state of AI. They discuss AI adoption and safety, disappearing junior tech jobs, robotics, AI’s “jagged frontier” of intelligence, and the growing race between the U.S. and China. Along the way, they debate whether AI should optimize everything, or if some things are better left human. Featuring: Chris Benson – Website , LinkedIn , Bluesky , GitHub , X Daniel Whitenack – Website , GitHub , X Links: The 2026 AI Index Report Sponsors: Prediction Guard: A self-hosted AI control plane for running agents in high impact environments. predictionguard.com/practicalai Upcoming Events: Register for upcoming webinars here ! Midwest AI Summit 2026
China’s swift moves on brain-computer interfaces challenge Europe and the US
China’s swift moves on brain-computer interfaces challenge Europe and the US c.groth Tue, 06/02/2026 - 16:55 picture alliance / HPIC | stringer Comment Jun 03, 2026 2 min read China’s swift moves on brain-computer interfaces challenge Europe and the US China in March approved an invasive brain-computer interface (BCI, 脑机接口) for commercial use – the first country in the world to do so. Europe’s risk-averse and ethics-heavy approach to BCI governance may harm its ability to compete in this technology. The interface by Shanghai-based Neuracle Medical Technology (博睿康) has already helped 32 patients with spinal cord injuries to regain hand movement. It consists of a coin-sized electrode placed in the brain to pick up signals when a patient imagines movement. The signals are then wirelessly transmitted to a robotic glove. More than 30 hospitals across China now operate BCI units, with applications expanding to neurodegenerative and psychiatric care. Europe can also boast world-class academic research and pioneering firms in this area, such as MindMaze and CorTec , but it will need to strengthen support via policy and investment to ensure that its BCI industry isn’t left behind. Neuracle’s approval is evidence that Beijing sees this frontier technology as highly strategic and even militarily significant . In 2025, China introduced a roadmap for the development of world-class BCI companies by 2030, while its 15th Five Year Plan endorses BCI as a future industry. The government launc…
Startup offers free home cleaning—if it can record it all for robot training
The latest twist in paying humans to wear head cameras for robot training data.
China's Robotics Dream Began in 1972
a history!
Humanoid Robots Hit a Turning Point as Their Brains Catch Up
Humanoid Robots Hit a Turning Point as Their Brains Catch Up robyn.cherinka… Thu, 05/14/2026 - 13:28 In this article from IEEE Spectrum , TRI CEO Gill Pratt says humanoid robots are advancing as AI “brains” improve, but warns that real reasoning, data limits, and hype cycles still challenge meaningful, scalable deployment. Read the full article here . Image Apr 2, 2026 Robotics 1 Minute Read
[In the media] “Mathematical formulas can change the rules of competition”: RIKEN’s approach to physical AI (Nikkei Tech Foresight, May 7, 2026)
An interview with Takayuki Osa, Team Director of the Robot Learning Team, was published in Nikkei Tech Foresight on May 7, 2026. The article introduces recent advances in robot
MolmoAct 2: An open foundation for robots that work in the real world
MolmoAct 2 is a fully open robotics foundation model that brings faster, stronger 3D action reasoning to real-world robot tasks, alongside a major new bimanual manipulation dataset for researchers to study, reproduce, and build on.
Open Source Self-Driving with Comma AI
Autonomous driving is not just a big tech or closed-source game, it's becoming accessible through open innovation and real-world deployment. Dan and Chris sit down with Harald Schäfer, CTO at Comma AI, to explore how OpenPilot is bringing self-driving to everyday vehicles using open source AI. We dive into the intersection of machine learning, robotics, and simulation, including how world models are enabling training at scale and shaping the future of autonomy. Featuring: Harald Schäfer – LinkedIn Chris Benson – Website , LinkedIn , Bluesky , GitHub , X Daniel Whitenack – Website , GitHub , X Links: Comma Upcoming Events: Register for upcoming webinars here !
Real-time inference for robots at Physical Intelligence
How Physical Intelligence runs remote, real-time, robotic inference on Modal.
Import AI 451: Political superintelligence; Google's society of minds, and a robot drummer
Are there any genies that can be put back in the bottle?
Intelligent Robots in 2026: Are We There Yet? with Nikita Rudin - #760
Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion Robotics to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. The complete show notes for this episode can be found at…
Robot Learning from Any Images
Robot Learning from Any Images robyn.cherinka… Wed, 11/12/2025 - 14:54 We introduce RoLA, a framework that transforms any in-the-wild image into an interactive, physics-enabled robotic environment. Unlike previous methods, RoLA operates directly on a single image without requiring additional hardware or digital assets. Our framework democratizes robotic data generation by producing massive visuomotor robotic demonstrations within minutes from a wide range of image sources, including camera captures, robotic datasets, and Internet images. At its core, our approach combines a novel method for single-view physical scene recovery with an efficient visual blending strategy for photorealistic data collection. We demonstrate RoLA's versatility across applications like scalable robotic data generation and augmentation, robot learning from Internet images, and single-image real-to-sim-to-real systems for manipulators and humanoids. Video results are available at this https URL . Read More Image Sep 26, 2025 Robotics 1 Minute Read
SAFE: Multitask Failure Detection for Vision-Language-Action Models
SAFE: Multitask Failure Detection for Vision-Language-Action Models robyn.cherinka… Wed, 11/12/2025 - 14:45 While vision-language-action models (VLAs) have shown promising robotic behaviors across a diverse set of manipulation tasks, they achieve limited success rates when deployed on novel tasks out of the box. To allow these policies to safely interact with their environments, we need a failure detector that gives a timely alert such that the robot can stop, backtrack, or ask for help. However, existing failure detectors are trained and tested only on one or a few specific tasks, while generalist VLAs require the detector to generalize and detect failures also in unseen tasks and novel environments. In this paper, we introduce the multitask failure detection problem and propose SAFE, a failure detector for generalist robot policies such as VLAs. We analyze the VLA feature space and find that VLAs have sufficient highlevel knowledge about task success and failure, which is generic across different tasks. Based on this insight, we design SAFE to learn from VLA internal features and predict a single scalar indicating the likelihood of task failure. SAFE is trained on both successful and failed rollouts, and is evaluated on unseen tasks. SAFE is compatible with different policy architectures. We test it on OpenVLA, π0, and π0-FAST in both simulated and real-world environments extensively. We compare SAFE with diverse baselines and show that SAFE achieves state-of-the-art failu…
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation robyn.cherinka… Wed, 11/12/2025 - 14:40 Off-policy evaluation (OPE) estimates the performance of a target policy using offline data collected from a behavior policy, and is crucial in domains such as robotics or healthcare where direct interaction with the environment is costly or unsafe. Existing OPE methods are ineffective for high-dimensional, long-horizon problems, due to exponential blow-ups in variance from importance weighting or compounding errors from learned dynamics models. To address these challenges, we propose STITCH-OPE, a model-based generative framework that leverages denoising diffusion for long-horizon OPE in high-dimensional state and action spaces. Starting with a diffusion model pre-trained on the behavior data, STITCH-OPE generates synthetic trajectories from the target policy by guiding the denoising process using the score function of the target policy. STITCH-OPE proposes two technical innovations that make it advantageous for OPE: (1) prevents over-regularization by subtracting the score of the behavior policy during guidance, and (2) generates long-horizon trajectories by stitching partial trajectories together end-to-end. We provide a theoretical guarantee that under mild assumptions, these modifications result in an exponential reduction in variance versus long-horizon trajectory diffusion. Experiments on the D4RL and OpenAI Gym benchmarks show substantial improveme…
RL without TD learning
In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference (TD) learning (which has scalability challenges ), and scales well to long-horizon tasks. We can do Reinforcement Learning (RL) based on divide and conquer, instead of temporal difference (TD) learning. Problem setting: off-policy RL Our problem setting is off-policy RL . Let’s briefly review what this means. There are two classes of algorithms in RL: on-policy RL and off-policy RL. On-policy RL means we can only use fresh data collected by the current policy. In other words, we have to throw away old data each time we update the policy. Algorithms like PPO and GRPO (and policy gradient methods in general) belong to this category. Off-policy RL means we don’t have this restriction: we can use any kind of data, including old experience, human demonstrations, Internet data, and so on. So off-policy RL is more general and flexible than on-policy RL (and of course harder!). Q-learning is the most well-known off-policy RL algorithm. In domains where data collection is expensive ( e.g. , robotics , dialogue systems, healthcare, etc.), we often have no choice but to use off-policy RL. That’s why it’s such an important problem. As of 2025, I think we have reasonably good recipes for scaling up on-policy RL ( e.g. , PPO, GRPO, and their variants). However, we still haven’t found a “…
ByteDance Introduces Astra: A Dual-Model Architecture for Autonomous Robot Navigation
ByteDance introduces Astra, an innovative dual-model architecture revolutionizing robot navigation in complex indoor environments. The post ByteDance Introduces Astra: A Dual-Model Architecture for Autonomous Robot Navigation first appeared on Synced .
From research to startup: Polybot receives order for AI-based harvesting robotics
ELLIS Institute Tübingen and Tübingen AI Center achieve important milestone for innovation in automated agriculture.
From Code to Robots: The Top AI Trends Transforming Business and Life
Artificial intelligence is no longer a concept of the distant future – it’s here, evolving at a rapid pace and reshaping industries in real time. From healthcare to entertainment, AI’s influence is everywhere, sparking innovation, efficiency, and even ethical debates. But with so much happening at once, where exactly is the industry heading? To make […] The post From Code to Robots: The Top AI Trends Transforming Business and Life appeared first on TOPBOTS .
Humanoid Robots on the Rise: Industry Advances, Key Players, and Adoption Timelines
The robotics industry stands on the brink of a significant transformation, with many experts – including NVIDIA CEO Jensen Huang – suggesting that we might be approaching a "ChatGPT moment" for robotics. The post Humanoid Robots on the Rise: Industry Advances, Key Players, and Adoption Timelines appeared first on TOPBOTS .
Congratulations to Marco Pavone for a Robotics: Science and Systems Conference Best Paper Award!
Congratulations to Marco Pavone for winning the best paper award at the Robotics: Science and Systems Conference on AI Safety for autonomous systems.
Stanford AI Lab Papers and Talks at AAAI 2022
The 36th AAAI Conference on Artificial Intelligence (AAAI 2022) is being hosted virtually from February 22th - March 1st. We’re excited to share all the work from SAIL that’s being presented, and you’ll find links to papers, videos and blogs below. Feel free to reach out to the contact authors directly to learn more about the work that’s happening at Stanford. List of Accepted Papers Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams Authors : Erdem Bıyık, Anusha Lalitha, Rajarshi Saha, Andrea Goldsmith, Dorsa Sadigh Contact : ebiyik@stanford.edu Links: Paper | Video | 2nd Video | Website Keywords : bandits, multi-agent systems, collaboration, human-robot interaction, partner-awareness Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning Authors : Tong Mu, Georgios Theocharous, David Arbour, Emma Brunskill Contact : tongm@stanford.edu Links: Paper Keywords : reinforcement learning, constraints IS-Count: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling Authors : Chenlin Meng*, Enci Liu*, Willie Neiswanger, Jiaming Song, Marshall Burke, David Lobell, Stefano Ermon Contact : jesslec@stanford.edu Award nominations: Oral presentation Links: Paper | Blog Post | Website Keywords : remote sensing, sampling PantheonRL Authors : Bidipta Sarkar, Aditi Talati, Andy Shih, Dorsa Sadigh Contact : bidiptas@stanford.edu Links: Paper | Video | Website Keywords : multiagent reinforcement learning; soft…
Reward Isn't Free: Supervising Robot Learning with Language and Video from the Web
This work was conducted as part of SAIL and CRFM . Deep learning has enabled improvements in the capabilities of robots on a range of problems such as grasping 1 and locomotion 2 in recent years. However, building the quintessential home robot that can perform a range of interactive tasks, from cooking to cleaning, in novel environments has remained elusive. While a number of hardware and software challenges remain, a necessary component is robots that can generalize their prior knowledge to new environments, tasks, and objects in a zero or few shot manner. For example, a home robot tasked with setting the dining table cannot afford lengthy re-training for every new dish, piece of cutlery, or dining room it may need to interact with. A natural way to enable such generalization in our robots is to train them on rich data sources that contain a wide range of different environments, tasks, and objects. Indeed, this recipe of massive, diverse datasets combined with scalable offline learning algorithms (e.g. self-supervised or cheaply supervised learning) has been the backbone of the many recent successes of foundation models 3 in NLP 4 5 6 7 8 9 and vision 10 11 12 . Replicating these impressive generalization and adaptation capabilities in robot learning algorithms would certainly be a step toward robots that can be used in unstructured, real world environments. However, directly extending this recipe to robotics is nontrivial, as we neither have sufficiently large and diverse…
Stanford AI Lab Papers at CoRL 2021
The Conference on Robot Learning (CoRL 2021) will take place next week. We’re excited to share all the work from SAIL that will be presented, and you’ll find links to papers, videos and blogs below. Feel free to reach out to the contact authors directly to learn more about the work that’s happening at Stanford! List of Accepted Papers LILA: Language-Informed Latent Actions Authors : Siddharth Karamcheti*, Megha Srivastava*, Percy Liang, Dorsa Sadigh Contact : skaramcheti@cs.stanford.edu, megha@cs.stanford.edu Keywords : natural language, shared autonomy, human-robot interaction BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments Authors : Sanjana Srivastava*, Chengshu Li*, Michael Lingelbach*, Roberto Martín-Martín*, Fei Xia, Kent Vainio, Zheng Lian, Cem Gokmen, Shyamal Buch, C. Karen Liu, Silvio Savarese, Hyowon Gweon, Jiajun Wu, Li Fei-Fei Contact : sanjana2@stanford.edu Links: Paper | Website Keywords : embodied ai, benchmarking, household activities Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration Authors : Chen Wang, Claudia Pérez-D’Arpino, Danfei Xu, Li Fei-Fei, C. Karen Liu, Silvio Savarese Contact : chenwj@stanford.edu Links: Paper | Website Keywords : learning for human-robot collaboration, imitation learning DiffImpact: Differentiable Rendering and Identification of Impact Sounds Authors : Samuel Clarke, Negin Heravi, Mark Rau, Ruohan Gao, Jiajun Wu, Doug James, Jeannette Bohg Contact : spclar…
MIT simulator lets users design wide range of functional soft robots
MIT simulator lets users design wide range of functional soft robots aconner Mon, 06/10/2019 - 12:37 Article June 10 '19 Adam Conner-Simons, MIT CSAIL MIT simulator lets users design wide range of functional soft robots To get robots to do things, computer scientists often use systems called physics simulators that reflect how a robot’s actions will impact the real world. These simulators don’t work particularly well, however, when it comes to soft robots made of flexible, deformable materials. This is because the underlying physical laws of deformable objects are much more complicated, requiring a lot more computational power to simulate. But in a new paper, a team from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed a new simulator made specifically for soft robots, and have shown that it can realistically simulate an eclectic mix of robotic designs, from a crawling robot to a four-legged running robot. The simulator doesn’t just efficiently evaluate robot designs, but also provides feedback on how designs can be improved. (The system’s feedback is computed based on something called “the chain rule,” and so the team has dubbed the simulator “ChainQueen”.) The team developed a high-performance GPU implementation of the simulator that they hope to eventually make open-source. “We believe this system has the potential to dramatically accelerate the development of soft robots,” says PhD student Andrew Spielberg, one of the co-authors of the…
This robot helps you lift objects — by looking at your biceps
This robot helps you lift objects — by looking at your biceps rachelg Wed, 05/22/2019 - 10:30 Video May 22 '19 Rachel Gordon CSAIL system can mirror a user's motions and follow nonverbal commands by monitoring arm muscles. We humans are very good at collaboration. For instance, when two people work together to carry a heavy object like a table or a sofa, they tend to instinctively coordinate their motions, constantly recalibrating to make sure their hands are at the same height as the other person’s. Our natural ability to make these types of adjustments allows us to collaborate on tasks big and small. But a computer or a robot still can’t follow a human’s lead with ease. We usually either explicitly program them using machine-speak, or train them to understand our words, à la virtual assistants like Siri or Alexa. In contrast, researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) recently showed that a smoother robot-human collaboration is possible through a new system they developed, where machines help people lift objects by monitoring their muscle movements. Dubbed RoboRaise, the system involves putting electromyography (EMG) sensors on a user’s biceps and triceps to monitor muscle activity. Its algorithms then continuously detect changes to the person’s arm level, as well as discrete up-and-down hand gestures the user might make for finer motor control. The team used the system for a series of tasks involving picking up and assembling mock…
Giving robots a better feel for object manipulation
Giving robots a better feel for object manipulation rachelg Mon, 04/29/2019 - 13:27 Video April 29 '19 Rob Matheson Model improves a robot’s ability to mold materials into shapes and interact with liquids and solid objects. A new learning system developed by MIT researchers improves robots’ abilities to mold materials into target shapes and make predictions about interacting with solid objects and liquids. The system, known as a learning-based particle simulator, could give industrial robots a more refined touch — and it may have fun applications in personal robotics, such as modelling clay shapes or rolling sticky rice for sushi. In robotic planning, physical simulators are models that capture how different materials respond to force. Robots are “trained” using the models, to predict the outcomes of their interactions with objects, such as pushing a solid box or poking deformable clay. But traditional learning-based simulators mainly focus on rigid objects and are unable to handle fluids or softer objects. Some more accurate physics-based simulators can handle diverse materials, but rely heavily on approximation techniques that introduce errors when robots interact with objects in the real world. In a paper being presented at the International Conference on Learning Representations in May, the researchers describe a new model that learns to capture how small portions of different materials — “particles” — interact when they’re poked and prodded. The model directly learns fr…
Deep Reinforcement Learning: Pong from Pixels
--> This is a long overdue blog post on Reinforcement Learning (RL). RL is hot! You may have noticed that computers can now automatically learn to play ATARI games (from raw game pixels!), they are beating world champions at Go , simulated quadrupeds are learning to run and leap , and robots are learning how to perform complex manipulation tasks that defy explicit programming. It turns out that all of these advances fall under the umbrella of RL research. I also became interested in RL myself over the last ~year: I worked through Richard Sutton’s book , read through David Silver’s course , watched John Schulmann’s lectures , wrote an RL library in Javascript , over the summer interned at DeepMind working in the DeepRL group, and most recently pitched in a little with the design/development of OpenAI Gym , a new RL benchmarking toolkit. So I’ve certainly been on this funwagon for at least a year but until now I haven’t gotten around to writing up a short post on why RL is a big deal, what it’s about, how it all developed and where it might be going. Examples of RL in the wild. From left to right : Deep Q Learning network playing ATARI, AlphaGo, Berkeley robot stacking Legos, physically-simulated quadruped leaping over terrain. It’s interesting to reflect on the nature of recent progress in RL. I broadly like to think about four separate factors that hold back AI: Compute (the obvious one: Moore’s Law, GPUs, ASICs), Data (in a nice form, not just out there somewhere on the int…
Language-Guided World Models: A Model-Based Approach to AI Control
Khanh Nguyen, CHAI Postdoctoral Fellow, published a paper at the Fourth International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics (ACL 2024).