HTTP/2 301 server: GitHub.com content-type: text/html location: https://lucys0.github.io/awe/ x-github-request-id: 9B76:2916CC:85728A:95EB8D:69520B97 accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 05:03:19 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210051-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766984599.441876,VS0,VE199 vary: Accept-Encoding x-fastly-request-id: 7973d7d1dfd74cf21f94a1f5c8971555ae68f7c1 content-length: 162 HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 x-origin-cache: HIT last-modified: Mon, 13 Nov 2023 00:52:55 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"65517367-285f" expires: Mon, 29 Dec 2025 05:13:19 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 3924:3A7A40:84300D:94A912:69520B97 accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 05:03:19 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210051-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766984600.660253,VS0,VE215 vary: Accept-Encoding x-fastly-request-id: bd3b565c7f808c787e370124f3cfaa5b18ef995b content-length: 2769

Waypoint-Based Imitation Learning for Robotic Manipulation

• Lucy Xiaoyang Shi^*
• Archit Sharma^*
• Tony Z. Zhao
• Chelsea Finn

• Stanford University

While imitation learning methods have seen a resurgent interest for robotic manipulation, the well-known problem of compounding errors continues to afflict behavioral cloning (BC). Waypoints can help address this problem by reducing the horizon of the learning problem for BC, and thus, the errors compounded over time. However, waypoint labeling is underspecified, and requires additional human supervision. Can we generate waypoints automatically without any additional human supervision? Our key insight is that if a trajectory segment can be approximated by linear motion, the endpoints can be used as waypoints. We propose Automatic Waypoint Extraction (AWE) for imitation learning, a preprocessing module to decompose a demonstration into a minimal set of waypoints which when interpolated linearly can approximate the trajectory up to a specified error threshold. AWE can be combined with any BC algorithm, and we find that AWE can increase the success rate of state-of-the-art algorithms by up to 25% in simulation and by 4-28% on real-world bimanual manipulation tasks, reducing the decision making horizon by up to a factor of 10.

Waypoint-Based Imitation Learning for Robotic Manipulation

• Lucy Xiaoyang Shi^*
• Archit Sharma^*
• Tony Z. Zhao
• Chelsea Finn

• Stanford University
• ^* equal contribution

---

While imitation learning methods have seen a resurgent interest for robotic manipulation, the well-known problem of compounding errors continues to afflict behavioral cloning (BC). Waypoints can help address this problem by reducing the horizon of the learning problem for BC, and thus, the errors compounded over time. However, waypoint labeling is underspecified, and requires additional human supervision. Can we generate waypoints automatically without any additional human supervision? Our key insight is that if a trajectory segment can be approximated by linear motion, the endpoints can be used as waypoints. We propose Automatic Waypoint Extraction (AWE) for imitation learning, a preprocessing module to decompose a demonstration into a minimal set of waypoints which when interpolated linearly can approximate the trajectory up to a specified error threshold. AWE can be combined with any BC algorithm, and we find that AWE can increase the success rate of state-of-the-art algorithms by up to 25% in simulation and by 4-28% on real-world bimanual manipulation tasks, reducing the decision making horizon by up to a factor of 10.