
Aaron Borger, co‑founder and CEO of Orbital Robotics, presented the company’s vision for AI‑controlled robotic arms that can capture, refuel, repair, or de‑orbit spacecraft in orbit. The firm aims to provide space‑grade hardware and integrated software to any satellite operator, turning robotic servicing from a research concept into a commercial capability. The core technology relies on deep reinforcement learning trained in high‑fidelity simulation, but Borger emphasized the need for deterministic, 100 % reliable behavior in the safety‑critical space environment. To achieve this, the team augments neural networks with physics‑based models, accounts for dynamic coupling between arm motion and spacecraft attitude, and uses Monte Carlo verification to prove convergence within defined state‑space bounds. Multi‑agent policies further enable coordinated inspection of large structures while minimizing delta‑V fuel consumption. Examples included a sub‑orbital rocket that threw and caught a ball using a 3‑D‑printed arm, a simulated fleet of spacecraft that simultaneously points solar arrays, cameras, and avoids collisions, and a safety‑ellipse concept that guarantees safe trajectories even if a node loses communication. Borger highlighted that the same neural network governs all agents, allowing decentralized operation and graceful degradation. If successful, Orbital Robotics could dramatically lower the cost and risk of on‑orbit servicing, support debris removal, and accelerate the construction of lunar and orbital habitats. The technology promises a shift from human‑intensive EVA to autonomous robotic infrastructure, opening new revenue streams for satellite operators and shaping the future of sustainable space logistics.

Ford unveiled an engineering effort to launch a $30,000 electric vehicle by dramatically reducing battery size. The project, run out of California and headed by former Tesla engineer Allen Clark, focuses on “a thousand cuts” to cut costs while...

The video demonstrates how to integrate a Rockwell Automation PowerFlex 525 variable‑frequency drive into a Studio 5000 Logix Designer project using the vendor‑supplied PowerDevice Object Library. First, the presenter downloads the PowerDevice library, updates the drive’s connection format in the Device Definition dialog,...

The video documents the author’s first public ride in a Zoox autonomous vehicle in Las Vegas, part of a limited free‑service pilot that requires only a credit‑card‑linked app download. The eight‑seat pod offers individual climate and music controls at four user...

DiskChunGS introduces a scalable 3D Gaussian splatting SLAM pipeline that overcomes traditional GPU memory constraints by treating scene reconstruction as a spatial streaming problem. The system partitions the environment into discrete chunks, keeping only the currently visible regions in GPU...

The video deconstructs the current hype around driverless cars, highlighting recent milestones such as New York City’s first permit for autonomous testing by Whimo. Even with this approval, the vehicles operate on a handful of streets and rely on a...

The session, led by PX4 maintainer Benjamin and Linux Foundation’s Ramon, introduced a new workflow for achieving precision landing on drones by integrating the PX4 autopilot stack with ROS 2. Key technical points included the use of PX4’s uORB middleware extended to...

The IROS 2025 keynote by Fumin Zhang examined how robots can perform high‑stakes search and rescue tasks by marrying classic search theory with modern generative AI and control techniques. Zhang highlighted that, despite a half‑century of research, the field has...

Fumiya Lida’s IROS 2025 keynote framed embodied intelligence as the reciprocal relationship between a body’s physical dynamics and the brain’s control mechanisms, challenging the longstanding brain‑versus‑body dualism that has split robotics from AI. He highlighted the staggering scale gap—30 trillion cells...

Li Zhang’s IROS 2025 keynote highlighted the rapid evolution of miniature biomedical robots, emphasizing magnetic actuation, bio‑hybrid materials, and modular architectures for safe, targeted therapy. He traced the concept back to Richard Feynman’s swallowable‑surgery vision and described how his team fabricates...

The IROS 2025 Human‑Robot Interaction keynote by Javier Alonso‑Mora centered on the challenges and breakthroughs in multi‑agent autonomy for mobile robots. He outlined how robots must not only navigate complex, dynamic environments but also cooperate with other robots and humans...

The keynote highlighted the limits of pure deep‑learning approaches for robot cognition, arguing that true general intelligence requires embodied, tactile experience. Perla Maiolino described how artificial skin (SciSkin) and distributed proximity sensors give robots a closed‑loop sense‑act‑perceive cycle, allowing safe,...

The lecture framed autonomous driving as the ultimate test for artificial intelligence, contrasting it with games like chess that have already been mastered by AI. While chess operates in a closed, rule‑bound environment, driving unfolds in an open system where...

The European Commission hosted a sectoral deep‑dive on AI in mobility, transport and automotive, outlining how the newly launched Apply AI strategy seeks to embed artificial intelligence across the EU’s transport ecosystem. Speakers Max Lea and Jakob Lman highlighted current...

The paper presents the first differentiable Model Predictive Control (MPC) framework that can vary its cost‑function weights online for constrained nonlinear systems, leveraging gradient‑based policy learning. A lightweight neural network receives real‑time observations—such as reference trajectory curvature and velocity—and outputs MPC...

Uber reported one of its strongest quarters, hitting a $15 billion annual trip run rate, 200 million monthly active users, record adjusted EBITDA of $2.5 billion and accelerating free cash flow while quarterly trips rose 22% and membership grew 55%...

The final project presentation of the Robotics Developer Masterclass showcased Aaron Emer’s "tic‑tac‑toe bot," a robotic arm that plays tic‑tac‑toe against a human opponent using computer vision and motion planning. The system combines the ROS framework, OpenCV for perception, MoveIt...