REVIEW 7 cited by
Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
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
read the original abstract
Legged robots navigating cluttered environments must be jointly agile for efficient task execution and safe to avoid collisions with obstacles or humans. Existing studies either develop conservative controllers (< 1.0 m/s) to ensure safety, or focus on agility without considering potentially fatal collisions. This paper introduces Agile But Safe (ABS), a learning-based control framework that enables agile and collision-free locomotion for quadrupedal robots. ABS involves an agile policy to execute agile motor skills amidst obstacles and a recovery policy to prevent failures, collaboratively achieving high-speed and collision-free navigation. The policy switch in ABS is governed by a learned control-theoretic reach-avoid value network, which also guides the recovery policy as an objective function, thereby safeguarding the robot in a closed loop. The training process involves the learning of the agile policy, the reach-avoid value network, the recovery policy, and an exteroception representation network, all in simulation. These trained modules can be directly deployed in the real world with onboard sensing and computation, leading to high-speed and collision-free navigation in confined indoor and outdoor spaces with both static and dynamic obstacles.
Forward citations
Cited by 7 Pith papers
-
When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual Auditing of Frozen Locomotion Policies
A counterfactual audit separates same-state headroom from recoverable state-allocation gain, returning NO-GO or ABSTAIN for learned command adapters on frozen Go2 and H1 locomotion policies at 1% thresholds.
-
When are safety filters safe? On minimum phase conditions of control barrier functions
Control barrier function safety filters can cause internal state divergence, and new minimum phase conditions are proposed to guarantee full-state boundedness.
-
Towards Understanding Adam Convergence on Highly Degenerate Polynomials
Adam achieves local linear convergence on highly degenerate polynomials without schedulers through second-moment decoupling that exponentially amplifies the effective learning rate.
-
Learning Agile Quadrotor Flight in the Real World
A self-adaptive drone controller learns from real-world flights alone, raising peak speed from ~2 m/s to 7.3 m/s in about 100 seconds near actuator saturation.
-
MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
A four-camera VLA navigation model trained by distilling multiple RL experts achieves strong simulation performance and qualitative real-world transfer.
-
KiVi: Kinesthetic-Visuospatial Integration for Dynamic and Safe Egocentric Legged Locomotion
A quadruped locomotion controller that explicitly separates proprioceptive and visual pathways stays stable under camera occlusion and visual corruption that destabilizes fused-vision policies.
-
Multi-Timescale Dynamics Model Bayesian Optimization for Plasma Stabilization in Tokamaks
A multi-timescale Bayesian optimization method using a neural dynamics model as a Gaussian process prior selected electron cyclotron heating profiles that avoided tearing instabilities in 4 of 8 live DIII-D tokamak sh...
Discussion (0). Sign in to comment.