SWAP: Symmetric Equivariant World-Model for Agile Robot Parkour
For legged locomotion, SWAP provides a structural prior that reduces learning burden and improves generalization, achieving record-breaking parkour performance.
SWAP embeds left-right symmetry equivariance into a latent world model for quadruped parkour, enabling a robot to break records with a 2.13 m gap leap and 1.63 m platform climb, while achieving zero-shot transfer to unseen terrains.
While latent world models enable the proactive predictions required for extreme parkour, their purely data-driven nature forces them to redundantly encode left-right symmetric interactions as independent patterns. This inflates the learning burden and hinders the capture of geometric regularities, restricting the latent space's efficiency for downstream policies. To address this, we propose SWAP, an end-to-end equivariant symmetric world model. This framework embeds symmetry directly into both the world model and the actor-critic networks. In real-world tests, the robot leaps across a 2.13 m gap and climbs a 1.63 m platform, breaking records for quadruped parkour. Furthermore, the framework exhibits robust geometric generalization to unseen mirrored terrains and exceptional zero-shot transferability across diverse outdoor environments. These results demonstrate that symmetry equivariance is an effective structural prior for pushing the physical boundaries of learned legged locomotion.