Video Friday: Your Robot Surgeon Will See You Now

2026-07-17 · Source: IEEE Spectrum · Field: Technology & Digital — Robotics & Autonomous Systems, Artificial Intelligence & Machine Learning · Depth: Intermediate, short

Summary

IEEE Spectrum Robotics' "Video Friday" presents a weekly roundup of robotics advancements and upcoming events, including the Summer School on Multi-Robot Systems (July 29–August 4, 2026), Actuate 2026 (August 18–19, 2026), IROS 2026 (September 27–October 1, 2026), and Humanoids Summit Seoul (September 22–23, 2026). Featured videos highlight UC San Diego's humanoid surgical teleoperation, Sunday Robotics' ACT-2 model for generalization, KAIST HOUND's APT-RL framework achieving 6 m/s locomotion, and Astribot's Lumo-2 robot learning model. Other demonstrations include Boston Dynamics' Spot for package delivery and Atlas at the FIFA World Cup 2026, LimX's long-horizon mobile manipulation, and EPFL LIS research on multifluid locomotion inspired by diving birds.

Key takeaway

For Robotics Engineers and Research Scientists tracking cutting-edge developments, this brief highlights significant progress in humanoid surgical applications, generalist robot learning models, and advanced quadrupedal locomotion. You should investigate the APT-RL framework for complex environment navigation and consider the implications of long-horizon mobile manipulation for future autonomous systems. Attend upcoming events like IROS 2026 to stay current on these rapidly evolving fields.

Key insights

Robotics advancements are pushing boundaries in surgical applications, generalist learning, and complex locomotion.

Principles

• Humanoids show promise for complex surgical tasks.
• Unified models enhance robot generalization and performance.
• Bio-inspired design aids multifluid locomotion.

Method

APT-RL uses Action Pretrained Transformer-based Reinforcement Learning for high-speed, multiskill quadrupedal locomotion, selecting and transitioning gaits with onboard perception.

In practice

• Evaluate humanoid platforms for surgical teleoperation.
• Explore transformer-based RL for dynamic robot control.
• Study bio-inspired designs for amphibious robots.

Topics

• Robotics
• Humanoid Robots
• Robot Learning
• Quadrupedal Locomotion
• Surgical Robotics
• Mobile Manipulation
• Reinforcement Learning

Best for: AI Scientist, Robotics Engineer, Research Scientist, AI Engineer

Related on AIssential

• Video Friday: Robotic Motion Discovery Reveals Unusual Behaviors — Robotics innovation spans humanoid loco-manipulation, domestic assistance, space operations, and open-source hardware for research.
• Intelligent Robots in 2026: Are We There Yet? [Nikita Rudin] - 760 — Bridging the sim-to-real gap and integrating semantics are critical for advanced robot autonomy and value generation.
• LEM Surgical - Dynamis Robotic Surgical System — Humanoid surgical robots can enhance precision and reduce workload in complex procedures.
• Video Friday: A World Cup for Robots — The robotics field is rapidly advancing, demonstrating complex multi-robot coordination, novel locomotion, and enhanced AI-driven dexterity.
• Track2Map: Online Deformable SLAM with Motion-Aware Pose Optimization in Robotic Surgery — Track2Map enables robust online deformable 3D reconstruction in robotic surgery by jointly optimizing camera pose and scene deformation.
• Humanoid robots controlled by surgeons did world-first operation on live pigs — Teleoperated humanoid robots performed world-first live animal surgery, offering a compact, lower-cost surgical access solution.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by IEEE Spectrum.