Beelines: Motion Prediction Metrics for Self-Driving Safety and Comfort

no code implementations • 1 Nov 2020 • Skanda Shridhar, Yuhang Ma, Tara Stentz, Zhengdi Shen, Galen Clark Haynes, Neil Traft

The commonly used metrics for motion prediction do not correlate well with a self-driving vehicle's system-level performance.

motion prediction

Interaction-Based Trajectory Prediction Over a Hybrid Traffic Graph

no code implementations • 27 Sep 2020 • Sumit Kumar, Yiming Gu, Jerrick Hoang, Galen Clark Haynes, Micol Marchetti-Bowick

Behavior prediction of traffic actors is an essential component of any real-world self-driving system.

Autonomous Driving Trajectory Prediction

Map-Adaptive Goal-Based Trajectory Prediction

no code implementations • 9 Sep 2020 • Lingyao Zhang, Po-Hsun Su, Jerrick Hoang, Galen Clark Haynes, Micol Marchetti-Bowick

We present a new method for multi-modal, long-term vehicle trajectory prediction.

Trajectory Prediction

Goal-Directed Occupancy Prediction for Lane-Following Actors

no code implementations • 6 Sep 2020 • Poornima Kaniarasu, Galen Clark Haynes, Micol Marchetti-Bowick

Predicting the possible future behaviors of vehicles that drive on shared roads is a crucial task for safe autonomous driving.

Autonomous Driving