REVIEW 14 cited by
Barkour: Benchmarking Animal-level Agility with Quadruped Robots
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Animals have evolved various agile locomotion strategies, such as sprinting, leaping, and jumping. There is a growing interest in developing legged robots that move like their biological counterparts and show various agile skills to navigate complex environments quickly. Despite the interest, the field lacks systematic benchmarks to measure the performance of control policies and hardware in agility. We introduce the Barkour benchmark, an obstacle course to quantify agility for legged robots. Inspired by dog agility competitions, it consists of diverse obstacles and a time based scoring mechanism. This encourages researchers to develop controllers that not only move fast, but do so in a controllable and versatile way. To set strong baselines, we present two methods for tackling the benchmark. In the first approach, we train specialist locomotion skills using on-policy reinforcement learning methods and combine them with a high-level navigation controller. In the second approach, we distill the specialist skills into a Transformer-based generalist locomotion policy, named Locomotion-Transformer, that can handle various terrains and adjust the robot's gait based on the perceived environment and robot states. Using a custom-built quadruped robot, we demonstrate that our method can complete the course at half the speed of a dog. We hope that our work represents a step towards creating controllers that enable robots to reach animal-level agility.
Forward citations
Cited by 14 Pith papers
-
High-speed control and navigation for quadrupedal robots on complex and discrete terrain
A hierarchical planner-plus-tracker system enables a quadruped to run on walls, clear a 1.3 m gap, and navigate discrete terrain at up to 4 m/s using a competitive generative curriculum.
-
MuJoCo Playground
An open-source, MJX-based robot learning framework with integrated batch rendering that provides fast training and demonstrates sim-to-real transfer on six robot platforms.
-
Generalized Locomotion in Out-of-distribution Conditions with Robust Transformer
A transformer with body tokenization and consistent dropout generalizes to unseen leg damages and sensor noise while trained on limited dynamics and clean observations.
-
Learning Impact-Rich Rotational Maneuvers via Centroidal Velocity Rewards and Sim-to-Real Techniques: A One-Leg Hopper Flip Case Study
A centroidal angular velocity reward, combined with actuator operating-region modeling and transmission load penalties, produces the first demonstrated full front flip on a one-leg hopper.
-
Towards Embodiment Scaling Laws in Robot Locomotion
A policy trained on about one thousand simulated robot bodies generalizes progressively better to unseen bodies as the number of training bodies grows, and it transfers zero-shot to two real robots.
-
Discovery of skill switching criteria for learning agile quadruped locomotion
A hierarchical reinforcement learning framework lets a quadruped robot automatically switch between trotting, bounding, galloping, and fall recovery based on distance to the goal, with switch distances tuned by CMA-ES.
-
DreamFLEX: Learning Fault-Aware Quadrupedal Locomotion Controller for Anomaly Situation in Rough Terrains
DreamFLEX uses an explicit fault-estimation network to detect broken leg joints and modulate a learned locomotion policy, letting a quadruped traverse rough terrain with fewer working legs.
-
Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning
A hybrid method uses LLM-generated candidate gaits and then refines them with a few human preference rankings, achieving quadruped behaviors aligned with user intent in as few as four queries.
-
SLIM: Sim-to-Real Legged Instructive Manipulation via Long-Horizon Visuomotor Learning
A single policy trained purely in simulation with a hierarchical teacher-student pipeline solves long-horizon search-grasp-transport-drop tasks on a low-cost quadruped with about 78% real-world success.
-
Reinforcement Learning from Wild Animal Videos
A quadruped robot acquires walking, jumping, running-like, and standing skills using only the output of a video classifier trained on wild-animal videos as its reinforcement learning reward.
-
Skill-Nav: Enhanced Navigation with Versatile Quadrupedal Locomotion via Waypoint Interface
A waypoint-based interface between planners and a trained quadrupedal locomotion policy enables navigation over diverse obstacles in simulation and on a real robot.
-
QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
Compressing 10-step action chunks into discrete latent codes lets an 8B multimodal model drive a quadruped at controller frequency and raises average task success by about 65%.
-
Improving generalization of robot locomotion policies via Sharpness-Aware Reinforcement Learning
SHAC-ASAM, which wraps the SHAC policy gradient with ASAM, shows improved tolerance to action noise and friction variations in simulated Ant and Humanoid walking tasks, but does not measure whether the learned minima ...
-
Advances, challenges, and opportunities for legged robots
Legged robots can now walk reliably across rough terrain, and the field's next bottleneck is semantic understanding and dexterous foot placement.
Discussion (0). Continue with ORCID to comment.