Around the World: Unified Learned Locomotion on a 270 g Continuous-Rotation Quadruped
cs.RO
Submitted: 2026-10-02
Updated: 2026-10-02
Comments: 13 pages, including appendices. Project website: https://submissionreview.github.io/around-the-world/
Project page: https://submissionreview.github.io/around-the-world
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior
- Tiny Reinforcement Learning for Quadruped Locomotion using Decision Transformers
- MiNI-Q: A Miniature, Wire-Free Quadruped with Unbounded, Independently Actuated Leg Joints
- Design of Q8bot: A Miniature, Low-Cost, Dynamic Quadruped Built with Zero Wires
- Stanford Pupper: A Low-Cost Agile Quadruped Robot for Benchmarking and Education
- Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller
- RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control
- CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs
- Proximal Policy Optimization Algorithms
- AllGaits: Learning All Quadruped Gaits and Transitions
- ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots
- Rapid Locomotion via Reinforcement Learning
- Barkour: Benchmarking Animal-level Agility with Quadruped Robots
- Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies