[IROS'24] PhysORD: A Neuro-Symbolic Approach of Physics-infused Motion Prediction in Offroad Driving

Title: PhysORD: A Neuro-Symbolic Approach of Physics-infused Motion Prediction in Offroad Driving
Authors: Zhipeng Zhao, Bowen Li, Yi Du, Taimeng Fu, Chen Wang.
Paper: arxiv.org/abs/...
Code: github.com/sai...
Website: sairlab.org/ph...
Abstract: We present PhysORD, a neural-symbolic approach integrating the conservation law, i.e., the Euler-Lagrange equation, into data-driven neural models for motion prediction in off-road driving. Our experiments showed that PhysORD can accurately predict vehicle motion and tolerate external disturbance by modeling uncertainties. It outperforms existing methods both in accuracy and efficiency and demonstrates data-efficient learning and generalization ability in long-term prediction.