DribbleBot: Dynamic Legged Manipulation in the Wild

Ji, Yandong; Margolis, Gabriel B.; Agrawal, Pulkit

doi:10.1109/icra48891.2023.10160325

Cited by 19 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, dribbling a soccer ball requires a legged robot to run while simultaneously applying forces with the feet to control the soccer ball, a body with its own distinct dynamics. Ji et al (2023) modeled the variable drag dynamics of interaction between a soccer ball and different surfaces, which enabled an adaptive policy to dribble the ball across pavement, grass, and mud. Another task beyond locomotion is to control a quadruped with a mounted arm, which incurs a change in robot dynamics as well as additional actuated degrees of freedom.…”

Section: Perspective On the Field And Future Directionsmentioning

confidence: 99%

Rapid locomotion via reinforcement learning

Margolis,

Yang,

Paigwar

et al. 2024

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots. We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9 m/s. This system runs and turns fast on natural terrains like grass, ice, and gravel and responds robustly to disturbances. Our controller is a neural network trained in simulation via reinforcement learning and transferred to the real world. The two key components are (i) an adaptive curriculum on velocity commands and (ii) an online system identification strategy for sim-to-real transfer. Videos of the robot’s behaviors are available at https://agility.csail.mit.edu/ .

show abstract

Section: Perspective On the Field And Future Directionsmentioning

confidence: 99%

Rapid locomotion via reinforcement learning

Margolis,

Yang,

Paigwar

et al. 2024

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

show abstract

SYNLOCO‐VE: Synthesizing central pattern generator with reinforcement learning and velocity estimator for quadruped locomotion

Zhang,

Xiao,

Zhou

et al. 2024

Optim Control Appl Methods

View full text Add to dashboard Cite

It is a challenging task to learn a robust and natural locomotion controller for quadruped robots at different terrains and velocities. In particular, the locomotion learning task will be even more difficult for the case with no exteroceptive sensors. In this article, the learning‐based locomotion control is, therefore, investigated for quadruped robots only using proprioceptive sensors. A new framework called SYNLOCO‐VE is proposed by synthesizing a feedforward gait planner, a trunk velocity estimator, and reinforcement learning (RL). The feedforward gait planner is developed based on the well‐known central pattern generator, but it can change the foot length for improved velocity tracking performance. The trunk velocity estimator is designed based on deep learning, which estimates the trunk velocity using historical data from proprioceptive sensors. The introduction of the trunk velocity estimator can mitigate the influence of the partial observation issue due to the lack of exteroceptive sensors. RL is employed to learn a feedback controller to regulate the robot gaits using feedback from proprioceptive sensors and the trunk velocity estimation. In the proposed framework, the feedforward gait planner can also guide the training process of RL, thus resulting in more stable and faster policy learning. Ablation studies are provided to demonstrate the efficiency of different modules in the proposed design. Extensive experiments are performed using a quadruped robot Go1, which only has proprioceptive sensors. The proposed framework is able to learn robust and stable locomotion at different terrains and tasks. Experimental comparisons are also conducted to illustrate the advantages of the proposed design over the state‐of‐the‐art methods.

show abstract

ViT-A: Legged Robot Path Planning using Vision Transformer A

Liu,

Lyu,

Hadjivelichkov

et al. 2023

2023 IEEE-RAS 22nd International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

DribbleBot: Dynamic Legged Manipulation in the Wild

Cited by 19 publications

References 31 publications

Rapid locomotion via reinforcement learning

Rapid locomotion via reinforcement learning

SYNLOCO‐VE: Synthesizing central pattern generator with reinforcement learning and velocity estimator for quadruped locomotion

ViT-A: Legged Robot Path Planning using Vision Transformer A

Contact Info

Product

Resources

About

DribbleBot: Dynamic Legged Manipulation in the Wild

Cited by 19 publications

References 31 publications

Rapid locomotion via reinforcement learning

Rapid locomotion via reinforcement learning

SYNLOCO‐VE: Synthesizing central pattern generator with reinforcement learning and velocity estimator for quadruped locomotion

ViT-A*: Legged Robot Path Planning using Vision Transformer A*

Contact Info

Product

Resources

About

ViT-A: Legged Robot Path Planning using Vision Transformer A