The MIT Humanoid Robot: Design, Motion Planning, and Control For Acrobatic Behaviors
Not on the map. Why?
Abstract (arXiv)
Demonstrating acrobatic behavior of a humanoid robot such as flips and spinning jumps requires systematic approaches across hardware design, motion planning, and control. In this paper, we present a new humanoid robot design, an actuator-aware kino-dynamic motion planner, and a landing controller as part of a practical system design for highly dynamic motion control of the humanoid robot. To achieve the impulsive motions, we develop two new proprioceptive actuators and experimentally evaluate their performance using our custom-designed dynamometer. The actuator's torque, velocity, and power limits are reflected in our kino-dynamic motion planner by approximating the configuration-dependent reaction force limits and in our dynamics simulator by including actuator dynamics along with the robot's full-body dynamics. For the landing control, we effectively integrate model-predictive control and whole-body impulse control by connecting them in a dynamically consistent way to accomplish both the long-time horizon optimal control and high-bandwidth full-body dynamics-based feedback. Actuators' torque output over the entire motion are validated based on the velocity-torque model including battery voltage droop and back-EMF voltage. With the carefully designed hardware and control framework, we successfully demonstrate dynamic behaviors such as back flips, front flips, and spinning jumps in our realistic dynamics simulation.
Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Apr 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 1; 2023: 5; 2024: 10; 2025: 8; 2026: 4.
28 papers.
Sort:
By area:
- 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
- 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
- 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
- 2022Rapid Locomotion via Reinforcement Learningcited by 130
- 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
- 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
- 2024ExBody2: Advanced Expressive Humanoid Whole-Body Controlcited by 75
- 2025HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpitcited by 65
- 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 63
- 2024Humanoid Locomotion as Next Token Predictioncited by 63
- 2025Embodied AI Agents: Modeling the Worldcited by 57
- 2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Controlcited by 47
16 more
- 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learningcited by 38
- 2025What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?cited by 37
- 2023Learning and Adapting Agile Locomotion Skills by Transferring Experiencecited by 25
- 2025Learning Getting-Up Policies for Real-World Humanoid Robotscited by 21
- 2025From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robotscited by 16
- 2024FLD: Fourier Latent Dynamics for Structured Motion Representation and Learningcited by 14
- 2024A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Taskscited by 14
- 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructionscited by 10
- 2024Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Modelscited by 8
- 2023Benchmarking Potential Based Rewards for Learning Humanoid Locomotioncited by 7
- 2025Let Humanoids Hike! Integrative Skill Development on Complex Trailscited by 4
- 2026Learning Human-Like Badminton Skills for Humanoid Robotscited by 3
- 2023Proprioceptive External Torque Learning for Floating Base Robot and its Applications to Humanoid Locomotioncited by 2
- 2026UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Modelscited by 1
- 2025Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terraincited by 0
- 2026Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Trackingcited by 0
- 2026UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models22 Jun 2026
- 2026Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking22 May 2026
- 2026Learning Human-Like Badminton Skills for Humanoid Robots9 Feb 2026
- 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions19 Jan 2026
- 2025What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?30 Dec 2025
- 2025Embodied AI Agents: Modeling the World27 Jun 2025
- 2025From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots15 Jun 2025
- 2025Let Humanoids Hike! Integrative Skill Development on Complex Trails9 May 2025
- 2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control6 May 2025
- 2025Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain14 Apr 2025
- 2025HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit18 Feb 2025
- 2025Learning Getting-Up Policies for Real-World Humanoid Robots17 Feb 2025
16 more
- 2024ExBody2: Advanced Expressive Humanoid Whole-Body Control17 Dec 2024
- 2024A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks29 Oct 2024
- 2024Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models30 Sep 2024
- 2024Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning26 Aug 2024
- 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI9 Jul 2024
- 2024HumanPlus: Humanoid Shadowing and Imitation from Humans15 Jun 2024
- 2024Humanoid Locomotion as Next Token Prediction29 Feb 2024
- 2024Expressive Whole-Body Control for Humanoid Robots26 Feb 2024
- 2024FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning21 Feb 2024
- 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control30 Jan 2024
- 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis14 Dec 2023
- 2023Proprioceptive External Torque Learning for Floating Base Robot and its Applications to Humanoid Locomotion8 Sep 2023
- 2023Benchmarking Potential Based Rewards for Learning Humanoid Locomotion19 Jul 2023
- 2023Learning and Adapting Agile Locomotion Skills by Transferring Experience19 Apr 2023
- 2023Real-World Humanoid Locomotion with Reinforcement Learning6 Mar 2023
- 2022Rapid Locomotion via Reinforcement Learning5 May 2022
- 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
- 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
- 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
- 2022Rapid Locomotion via Reinforcement Learningcited by 130
- 2024Expressive Whole-Body Control for Humanoid Robotscited by 117
- 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
- 2024ExBody2: Advanced Expressive Humanoid Whole-Body Controlcited by 75
- 2025HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpitcited by 65
- 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 63
- 2024Humanoid Locomotion as Next Token Predictioncited by 63
- 2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Controlcited by 47
- 2023Learning and Adapting Agile Locomotion Skills by Transferring Experiencecited by 25
12 most cited of 24 All 24 (JSON)
- 2026Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking22 May 2026
- 2026Learning Human-Like Badminton Skills for Humanoid Robots9 Feb 2026
- 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions19 Jan 2026
- 2025From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots15 Jun 2025
- 2025Let Humanoids Hike! Integrative Skill Development on Complex Trails9 May 2025
- 2025AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control6 May 2025
- 2025Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain14 Apr 2025
- 2025HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit18 Feb 2025
- 2025Learning Getting-Up Policies for Real-World Humanoid Robots17 Feb 2025
- 2024ExBody2: Advanced Expressive Humanoid Whole-Body Control17 Dec 2024
- 2024A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks29 Oct 2024
- 2024Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models30 Sep 2024
12 newest of 24 All 24 (JSON)