Deep Robotics
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
DARPA readies robotic deep-space repair satellite for 2026 launch
DARPA's Robotic Servicing of Geosynchronous Satellites (RSGS) payload resides in the cryogenic thermal vacuum chamber at the U.S. Naval Research Laboratory’s Naval Center for Space Technology in Washington, D.C., on Oct. 8, 2024.
Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
arXiv:2606.01892v1 Announce Type: new Abstract: Robot localization systems are critical for autonomous navigation and safety. Adversarial perturbations can mislead these systems, resulting in mislocalization, navigation errors, or unsafe interactions, especially in mission-critical scenarios. This paper investigates the vulnerability of deep learning based localization pipelines to adversarial attacks.
S2M-Trek: From Single to Multi-Sphere Transport via Per-Frame Deep Sets on a Wheel-Legged Robot
new Abstract: We study the problem of scaling dynamic loco-manipulation from a single free-rolling sphere to multiple spheres transported simultaneously on the back of a wheel-legged quadruped, without fences, grippers, or mechanical stops. Multiple identical free-rolling spheres form an unordered set with no persistent identity: their ordering may change independently at each history frame, creating a \emph{per-frame permutation symmetry} that standard history-concatenation set encoders do...
ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration
arXiv:2606.09381v1 Announce Type: new Abstract: Learning robot manipulation policies with deep neural networks from a single demonstration remains highly challenging, as even small deviations from the demonstrated trajectory can quickly compound into failure, while collecting substantial online interaction data is costly. We propose ReGIL, a retrieval-guided imitation learning framework that treats a single demonstration as an external memory. ReGIL repeatedly queries this static memory...
Do We Really Need Immediate Resets? Rethinking Collision Handling for Efficient Robot Navigation
Announce Type: replace Abstract: Should a single collision necessarily terminate an entire navigation episode? In most deep reinforcement learning (DRL) frameworks for robot navigation, this remains the standard practice: every collision immediately triggers a global environment reset and is penalized as a complete task failure. While a collision during deployment naturally indicates task failure, applying the same treatment during training prevents the agent from exploring challenging...
AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation
arXiv:2606.03963v2 Announce Type: replace Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design,...
Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation
arXiv:2606.03963v1 Announce Type: new Abstract: Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design, policy...
Unitree clears key hurdle to Shanghai IPO as China’s humanoid robot wave gathers pace
Unitree clears key hurdle to Shanghai IPO as China’s humanoid robot wave gathers pace Listing plan highlights Unitree’s push to invest more in robot ‘brains’ as it joins competitors in China’s humanoid rush The Hangzhou-based company filed to list on Shanghai’s Star Market on March 20. Following two rounds of regulatory inquiries and an on-site inspection, the hearing approval opens the door for the IPO to proceed to registration and issuance. Unitree said it aimed to raise 4.2 billion yuan...
Meta acquires robotics AI startup as it makes the push into humanoid machines
Meta acquires robotics AI startup as it makes the push into humanoid machines Meta has purchased Assured Robot Intelligence (ARI), a startup company that's building artificial intelligence for robots in order to "address critical challenges" in "high-value labor markets." The company is already working on robot hardware and AI in-house, but a spokesperson told Bloomberg that ARI "will bring a deep expertise in how [it] can design [its] models and frontier capabilities for robot control and...
Inside Amazon’s busiest European warehouse, where robots, lasers and humans deliver the future
Amazon says robots will make work safer and deliveries faster. Euronews Next saw them in action. Amazon used its Delivering the Future event on Thursday in the United Kingdom to make a series of major announcements for Europe, promising billions in new investment, thousands of jobs and a new generation of robots that could reshape the lives of consumers, warehouse workers and the wider logistics economy.