Boston Dynamics Tests Whole-Body Control of Atlas Humanoid with Wheel Integration
- Published
- Source
- TheRobotReport.com
Boston Dynamics has released a video showcasing its Atlas humanoid robot equipped with wheels for enhanced mobility. This experiment merges classical model-based motor control with whole-body reinforcement learning to improve dynamic stability in unpredictable environments. Andy Wu, a controls engineer at Boston Dynamics, emphasized the importance of understanding adaptability in real-world conditions through this innovative approach.
The integration of wheels allows Atlas to perform various maneuvers, including fast rolling on flat surfaces and navigating obstacles with articulated legged motion. Wu noted that the system learned these behaviors in simulation before executing them in real life with impressive accuracy. The simplicity of the retrofit process, akin to changing a bicycle wheel, highlights the design efficiency of Atlas for high-volume production and serviceability.
Boston Dynamics aims to further investigate the policy response to actuator failures, which is crucial for safety and system reliability. The experiment underscores the benefits of combining classical motor controls with whole-body reinforcement learning, resulting in enhanced agility and adaptability in real-world scenarios.
Original report
Boston Dynamics adds wheels to Atlas humanoid to test whole-body control
TheRobotReport.com · Mike OitzmanThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
-
8
RobotToday Weekly November 2 – 6, 2026 RobotToday · 2 days ago
- 9
- 10
- 11
- 12
Related Suppliers
Boston Dynamics
Iconic US robotics firm (MIT spin-off, 1992); Spot quadruped, Atlas humanoid, Stretch warehouse robot; owned by Hyundai; ~$21B valuation.
Atlas Copco AB
Swedish multinational industrial company supplying compressors, vacuum equipment, industrial tools, and automated assembly solutions to manufacturers worldwide.
Atlas Copco Tools Central Europe GmbH
Distributor of Atlas Copco assembly tools and fastening solutions for Germany, Austria, Switzerland, Belgium and the Netherlands.
TRACLabs, Inc.
NASA-partnered robotics software company specializing in human-robot interfaces, electronic procedures, and autonomous task planning.
Bauman Moscow State Technical University
Moscow, Russia technical university founded 1830; organizes engineering research into seven directions including industrial, household, and medical robotics.
Shanghai STEP Electric Corporation 上海新时达电气股份有限公司
Shanghai maker of elevator controls, servo drives and STEP/ADTECH industrial, SCARA, wafer and collaborative robots with in-house controllers; Haier-backed.
Chang Robotics
Jacksonville Beach, Florida DBE-certified robotics engineering firm founded 2017 by Matthew Chang; runs Curabotics, its hospital-automation division.
Venturi Space
Monaco-based lunar mobility company making hyper-deformable wheels and batteries for Venturi Astrolab rovers and building the 750 kg MONA LUNA rover.
Chengdu Leen Automation Technology Co., Ltd. 成都乐恩自动化技术有限公司
Chengdu maker of servo drives and harmonic, planetary, and cycloidal reducer motors for aerospace, defense, nuclear, and medical robotics applications.
Dynamic Creatures
Boston spin-out of Boston Dynamics building interactive character robots for theme parks and hotels on its SnowJay platform; launched Sept 2026.
Delta Intelligence 德塔智能
Beijing embodied-AI startup founded 2026 building the Delta-0 humanoid foundation model and D1 data-capture rigs; about RMB 1.2bn raised in six rounds.
Beijing Institute for General Artificial Intelligence 北京通用人工智能研究院
Beijing non-profit AGI institute led by Zhu Songchun whose embodied-AI stack includes the TongBrain robot brain and the open-source TongSIM simulator.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.