{
  "id": 19303979,
  "title": "Boston Dynamics Adds Wheels to Atlas Humanoid",
  "url": "https://urgent.news/2026/11/10/boston-dynamics-adds-wheels-to-atlas-humanoid",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-10T07:00:00.000Z",
  "source": {
    "name": "Slashdot",
    "slug": "slashdot",
    "url": "https://hardware.slashdot.org/story/26/11/09/2317206/boston-dynamics-adds-wheels-to-atlas-humanoid"
  },
  "original_language": "en",
  "account": "Boston Dynamics has added wheels to its Atlas humanoid robot, enabling it to swiftly traverse flat ground while still utilizing its articulated legs to maneuver around obstacles and uneven terrain. The experiment merges traditional model-based motor control with whole-body reinforcement learning to ensure dynamic stability across unstructured, real-world environments. In addition to mastering wheel-based locomotion, Atlas can also execute pirouettes and other aggressive actuation maneuvers, showcasing its ability to seamlessly transition between fast rolling on flat surfaces and agile legged movement over obstacles or irregular surfaces.\n\nControls engineer Andy Wu trained the system in simulation, where it learned all the behaviors before successfully executing them in real life with impressive precision. The retrofit process was remarkably simple, involving the attachment of an off-the-shelf scooter rim onto Atlas's existing ankle actuator via a custom adapter – essentially the only new component required. Wu emphasized that the robot was designed for mass production and easy maintenance, making this retrofit akin to swapping a bicycle wheel. The software adaptation was equally straightforward, as each wheel is modeled as a continuously spinning ankle, requiring only the replacement of the feet with wheels in the existing robot model.\n\nLooking ahead, Wu aims to investigate the system's response to failed actuators, a crucial aspect of safety and understanding how the robot will react to potential failures. The key takeaway for Wu and the Boston Dynamics controls engineering team is the importance of control synergy, demonstrated by the video which reveals that combining classical motor controls for baseline stability with whole-body reinforcement learning for reactive adaptation results in superior real-world agility compared to using either approach alone.",
  "summary": "Boston Dynamics has equipped its Atlas humanoid with wheels, allowing the robot to rapidly roll across flat terrain while still using its articulated legs to navigate obstacles and uneven surfaces. \"The 'experiment' combined classical model-based motor control with whole-body reinforcement learning to maintain dynamic stability across unstructured, real-world terrain,\" reports The Robot Report.…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}