Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs

Shi, Fan; Homberger, Timon; Lee, Joonho; Miki, Takahiro; Zhao, Moju; Farshidian, Farbod; Okada, Kei; Inaba, Masayuki; Hutter, Marco

doi:10.1109/icra48506.2021.9561926

Cited by 26 publications

(12 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advances in reinforcement learning (RL) algorithms and computational hardware have enabled rapid progress in using these algorithms for tasks on real robots. Techniques such as domain randomization and large-scale training have enabled results across a variety of tasks with sim2real, including in-hand manipulation [3,13], as well as in legged locomotion [14,15]. Active identification of system parameters has also been shown to be helpful in the context of learning manipulation tasks [16].…”

Section: Related Workmentioning

confidence: 99%

Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger

Allshire¹,

Mittal²,

Lodaya³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a system for learning a challenging dexterous manipulation task involving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trained with NVIDIA's IsaacGym simulator. We show empirical benefits, both in simulation and sim-to-real transfer, of using keypoints as opposed to position+quaternion representations for the object pose in 6-DoF for policy observations and in reward calculation to train a model-free reinforcement learning agent. By utilizing domain randomization strategies along with the keypoint representation of the pose of the manipulated object, we achieve a high success rate of 83% on a remote TriFinger system maintained by the organizers of the Real Robot Challenge. With the aim of assisting further research in learning in-hand manipulation, we make the codebase of our system, along with trained checkpoints that come with billions of steps of experience available, at https://s2r2-ig.github.io

show abstract

Section: Related Workmentioning

confidence: 99%

Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger

Allshire¹,

Mittal²,

Lodaya³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…2) Legged Manipulation: Manipulation via locomotion has been studied in [22]- [26]. [24] proposed to use all the four legs of a quadrupedal robot as a dexterous manipulator by lying the robot back on the ground. However this scarifies the mobility of the legged system and makes it no difference from a four finger manipulator.…”

Section: Introductionmentioning

confidence: 99%

Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion

Cheng¹,

Kumar²,

Pathak³

2023

Preprint

View full text Add to dashboard Cite

Locomotion has seen dramatic progress for walking or running across challenging terrains. However, robotic quadrupeds are still far behind their biological counterparts, such as dogs, which display a variety of agile skills and can use the legs beyond locomotion to perform several basic manipulation tasks like interacting with objects and climbing. In this paper, we take a step towards bridging this gap by training quadruped robots not only to walk but also to use the front legs to climb walls, press buttons, and perform object interaction in the real world. To handle this challenging optimization, we decouple the skill learning broadly into locomotion, which involves anything that involves movement whether via walking or climbing a wall, and manipulation, which involves using one leg to interact while balancing on the other three legs. These skills are trained in simulation using curriculum and transferred to the real world using our proposed sim2real variant that builds upon recent locomotion success. Finally, we combine these skills into a robust longterm plan by learning a behavior tree that encodes a highlevel task hierarchy from one clean expert demonstration. We evaluate our method in both simulation and real-world showing successful executions of both short as well as long-range tasks and how robustness helps confront external perturbations. Videos at https://robot-skills.github.io

show abstract

“…Besides, Fan presented a novel quadruped manipulation skill for dexterous full-limb operation by deep reinforcement learning and verified by the rolling ball experiments. This approach is inspired by the legged animal's playful movement [7]. Another quadruped robot named ALPHRED showed great manipulation and locomotion abilities by the leg and manipulation arm converts.…”

Section: Introductionmentioning

confidence: 99%

A unified modeling and trajectory planning method based on system manipulability for the operation process of the legged locomotion manipulation system

Peng

Haibin

2023

Robotica

View full text Add to dashboard Cite

Flexibility is one of the most significant advantages of legged robots in unstructured environments. However, quadruped robots cannot interact with environments to complete some manipulation tasks. One effective way is to load a manipulation arm. In this paper, we exhibit a quadruped locomotion manipulation system (LMS) named HITPhanT. This system comprises a quadruped locomotion platform and a six-degree-of-freedom manipulation arm. Besides, when the LMS moves to a designated position for operation, it is necessary to constrain the foot contact points to avoid sliding. Therefore, the foot contact point is regarded as a spherical hinge. So the locomotion platform can be considered as a parallel mechanism. A hybrid kinematics model is established by considering the serial robotic arms connecting this parallel mechanism. Besides, the trajectory planning method, which improves the system’s manipulability in evaluating the system balance, is also proposed. Finally, corresponding experiments verify the overall system’s stabilization and algorithm’s effectiveness.

show abstract

Circus ANYmal: A Quadruped Learning Dexterous Manipulation with Its Limbs

Cited by 26 publications

References 43 publications

Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger

Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger

Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion

A unified modeling and trajectory planning method based on system manipulability for the operation process of the legged locomotion manipulation system

Contact Info

Product

Resources

About