Results for “Robots”

arXiv (research papers) Benjamin A. Christie

Inner Product Regularization for Imitation Learning

Robots that learn from demonstrations should extrapolate their policy despite state perturbations such as sensor noise, scene variation, and compounding errors. One approach to this robustness is regularization. Prior regularizers consider each state on its own and limit how sensitive the policy is to any perturbation at that state. By contrast, we explore how the policy's output shifts when given the same perturbation at different states. Our insight is that, locally, the…

Read at arXiv (research papers)

SiliconANGLE AI Kyt Dotson SI

Qvyon launches with $8M to improve safety for physical AI deployments

Physical AI validation infrastructure and software development company Qvyon Technologies Inc. launched today with $8 million in total funding to help companies validate autonomous vehicles and robots before deployment. MaC Venture Capital led the funding, with participation from BDC Capital, BKR Capital and Spotlight VP. Physical AI is artificial intelligence that moves from digital brains

Read at SiliconANGLE AI

arXiv (research papers) Yaru Niu

EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming

Generalist manipulation policies can benefit from the complementary experience of humans, real robots, and simulated agents. However, differences in morphology, sensing, and control interfaces make it difficult to learn effectively from their combined demonstrations. We introduce EgoX, an egocentric cross-embodiment learning framework that organizes heterogeneous demonstrations through semantically corresponding observation and action modalities. EgoX pretrains a Modularized…

Read at arXiv (research papers)

Tech.eu John Reynolds Startups

SoftBank leads $500M funding round in Agile Robots

SoftBank has led a $500m funding round in German humanoid robotics startup Agile Robots that automates industrial work.The Japanese multinational led the Series F funding round, which also features Nv...

Read at Tech.eu

arXiv (research papers) Shunya Tadano

Safe and Efficient Navigation Considering Texting Pedestrians via Attention-Aware Cost-map Tuning

Smartphone-distracted pedestrians deviate from social norms unpredictably and cannot be relied upon to yield to approaching robots -- a safety challenge that existing navigation methods are poorly equipped to handle, since they treat all pedestrians uniformly regardless of attention state. We propose an attention-aware navigation framework that classifies each pedestrian as attentive or distracted in real-time using 3D skeletal features and a Random Forest classifier, then…

Read at arXiv (research papers)

arXiv (research papers) Xincheng Tan

NSDL: Neuro-Symbolic Division of Labor for Multi-Robot Task Planning

Planning for a heterogeneous robot team from a scene image and an instruction involves two kinds of decisions. Some must be judged from the scene: which goals are already met, how the task splits, and which robot does what. Others follow from these and can be computed: prerequisite actions, handoffs between robots, and timing. We argue that each kind should go to the component suited to it: a small vision-language model learns the first, and a deterministic solver computes…

Read at arXiv (research papers)

arXiv (research papers) Yonghwan Kim

Autonomous Mobile Robots on a Computing Field

We introduce CABOT, a computational model for autonomous mobile robots in which the discrete plane the robots operate on is not a passive stage but an active computing medium. In the classical Look-Compute-Move (LCM) model every increase in computational capability is obtained by strengthening the robots themselves, with lights, memory or wider visibility, at a cost paid once per robot. CABOT strengthens the environment instead: each cell of the grid holds a state from a…

Read at arXiv (research papers)

arXiv (research papers) Pengfei Ye

Reins: Frontier Multimodal Models Driving Real Robot Arms on Long-Horizon Tasks, Zero-Shot

Frontier models such as GPT-6.1 Sol, GPT-6 Astra and Claude Opus 5.5 can now plan and call tools, yet they still struggle to drive real robots through long-horizon, contact-rich manipulation, blind while the arm moves and while they think. We present Reins, a harness in which an off-the-shelf model operates a dual-arm robot with 3D perception tools and atomic actions that report contact and grip. The model chains actions in one call, each with a condition that must hold…

Read at arXiv (research papers)

Tech in Asia Aiko Gao Ishida Startups

SoftBank leads $500m bet on German robot maker Agile Robots

The company plans to expand in the US, add production capacity, including in Germany, and enter new markets.

Read at Tech in Asia

IoT Insider Tomohide Yamazaki

Wireless reliability under industrial pressure

Automated guided vehicles (AGVs) and autonomous mobile robots (AMRs) are becoming central to smart factories and warehouses as manufacturers look to tackle labour shortages and improve productivity. In factories and warehouses, transport robots move parts, pallets, and finished goods between production lines, storage areas, and packing stations. In e-commerce fulfilment centres, AMRs are also increasingly…

Read at IoT Insider

Human Rights Watch Human Rights Watch

Global Treaty Needed to Combat Autonomous Weapons Threat

Click to expand Image © 2022 Brian Stauffer for Human Rights Watch (Geneva, November 12, 2026) – The failure of states to take decisive action on autonomous weapons next week at the Review Conference of the Convention on Conventional Weapons (CCW) would leave civilians dangerously exposed to rapidly advancing military technologies, Amnesty International, Human Rights Watch, and Stop Killer Robots said today. The CCW is an international treaty prohibiting or restricting the…

Read at Human Rights Watch

EE Times Nitin Dahad SI

NXP CTO Lars Reger on Physical AI, Robots, Drones, and Trust

Explore NXP CTO Lars Reger’s view of physical AI beyond humanoids, from NavQ95 robot kits to edge trust, security, and geopolitics.

Read at EE Times

GeekWire Todd Bishop SI

Seattle VC firm Ascend closes $17M fund to back ‘Third Act’ startups in physical AI and hardware

Ascend, a venture firm that writes early checks into startups such as Overland AI and Endurance Energy, closed a $17 million third fund and landed its first institutional investor, FirstLook Partners. The fund will back companies building robots, energy systems, defense technology and other physical products that run on AI.

Read at GeekWire

SemiWiki Daniel Nenni SI

Why Video Processing Matters for the Next Generation of Robots

Mobilint has begun mass production of next-generation edge AI chips that incorporate video codec technology from Chips&Media, the companies announced on November 4. The South Korean partners are targeting robotics applications, including humanoids, where several cameras can generate more video than a system can easily…

Read at SemiWiki

The Verge Andrew J. Hawkins SI

Serve Robotics wants to democratize sidewalk delivery robots

Serve Robotics is opening up its platform to make its autonomous last-mile delivery robots available to anyone who wants to use them. The company is launching a new AV Delivery Developer Portal, enabling third-party software engineers, independent businesses, and even autonomous AI agents to access its fleet of 2,000 sidewalk robots. With this new capability,

Read at The Verge

VnExpress International

Robots perform martial arts, dance in lion costumes on HCMC's Nguyen Hue Walking Street

Robots performing martial arts moves and dancing in lion costumes drew crowds to Nguyen Hue Walking Street in Ho Chi Minh City on Oct. 26.

Read at VnExpress International

Future Farming Geert Hekkert

Study: Small field robots could cut onion growing costs by 75%

Small, battery-electric field robots could substantially reduce production costs in onions and lettuce, according to a new study published in Nature Communications. But the impressive savings are based on theoretical modelling, not field trials. Actual costs and benefits may differ considerably under commercial farming conditions.

Read at Future Farming

Tech in Asia Diya Lal Startups

SK hynix memory gets safety certification for cars, robots

In vehicles, LPDDR5X is marketed for use in advanced driver-assistance and infotainment systems.

Read at Tech in Asia

The Register Brandon Vigliarolo Security

Ring robots ready to patrol paranoids’ pads

Amazon calls its home security drone and business patrol bot 'proactive protection'

Read at The Register

The Decoder Maximilian Schreiner SI

Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot

Nvidia's new AI model GR00T 2 is designed to teach robots new tasks without laborious teleoperation. Instead, the system transfers human hand movements from videos to robotic arms, trained on about 400,000 hours of video footage. Success rates still vary widely, though, ranging from 10 to 80 percent depending on the task. The article Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot appeared first on The Decoder.

Read at The Decoder

TechCabal Kenn Abuya Startups

Acecore, Supplya and Navidyn are betting Nigeria can build, lend and dive

A battery manufacturer, a lender serving small retailers, and a developer of underwater robots took the top three spots at TechCabal (TC) Battlefield.

Read at TechCabal

The Decoder Maximilian Schreiner SI

Google DeepMind's Gemini Robotics 2.5 scores 96 percent sorting metal parts in a Mercedes-Benz assembly pilot

Google Deepmind introduced Gemini Robotics 2.5, a new control model for robots, and tested it with Apptronik on active Mercedes-Benz production lines in Hungary and Germany. The humanoid robot Apollo 2 sorted metal parts there with a reported success rate of 96 percent. The article Google DeepMind's Gemini Robotics 2.5 scores 96 percent sorting metal parts in a Mercedes-Benz assembly pilot appeared first on The Decoder.

Read at The Decoder

NBC News David K. Li

Amazon’s Ring debuts security robots including a drone

Amazon’s Ring has launched an indoor security drone, the company said Tuesday, offering homeowners room-to-room surveillance where a fixed camera cannot reach.

Read at NBC News

9to5Google Ben Schoon

Amazon’s new Ring cameras are mounted to roving robots, including $250 Drone Cam

Amazon’s Ring brand is today launching a new “Robotics” division that will start with two offerings – a $250 Ring Drone Cam and a $1,000 Rover Cam.

Read at 9to5Google

Hackster.io Nick Bild https://www.hackster.io/nickbild

Teaching Robots What Really Matters

MIT's FLEX teaches robots what really matters by turning simple natural language corrections into better behavior.

Read at Hackster.io

arXiv (research papers) Qinfeng Zhu

LEASH: Stay Safe in Agentic Robotics

Foundation models such as GPT and Claude have shown strong capabilities in spatial understanding and embodied intelligence. These advances make agentic robotics a promising path toward artificial general intelligence in robotics. However, we find that using foundation models to control robots poses serious safety risks, and comprehensive safety evaluation is still lacking. We introduce RoboRisk, a comprehensive benchmark for evaluating safety in agentic robotics. Its 92…

Read at arXiv (research papers)

9to5Mac Ben Lovejoy

Ring’s wheeled and flying robots will patrol your home

Some people use a whole bunch of fixed cameras to monitor their homes, but Amazon has just announced a more flexible solution through wheeled and flying robots. Both the $250 Drone Cam and $1,000 Rover Cam can respond to alarms or door and window sensor alerts in order to go check out what’s happening and send live video …

Read at 9to5Mac

About Amazon

Ring announces Ring Robotics, ushering in a new era of security

Ring Robotics is launching with two robots: Ring Drone Cam and Ring Rover Cam, providing mobile, proactive protection whenever and wherever you need it.

Read at About Amazon

arXiv (research papers) Kim Alexander Christensen

Persistent Metric-Semantic Maritime Scene Memory from Open-Vocabulary 3D Scene Graphs

Three-dimensional scene graphs (3DSGs) can provide robots with persistent metric-semantic representations for spatial reasoning, but the existing methods have primarily been developed for indoor and terrestrial environments. In this paper we investigate how a representative outdoor open-vocabulary method transfers to maritime environments and which adaptations are needed. Our experiments show that zero-shot representative outdoor 3DSG descriptions agree with our labeled…

Read at arXiv (research papers)

Older stories