TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning
By: Zebin Xing , Pengxuan Yang , Linbo Wang and more
Potential Business Impact:
Helps self-driving cars choose safer paths.
Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous work has demonstrated that models can achieve better planning performance when provided with a prior distribution of possible trajectories. However, these approaches often overlook two critical aspects: 1) The appropriate trajectory prior can vary significantly across different driving scenarios. 2) Their trajectory evaluation mechanism lacks policy-driven refinement, remaining constrained by the limitations of one-stage supervised training. To address these issues, we explore improvements in two key areas. For problem 1, we employ MoE to apply different trajectory priors tailored to different scenarios. For problem 2, we utilize Reinforcement Learning to fine-tune the trajectory scoring mechanism. Additionally, we integrate models with different perception backbones to enhance perceptual features. Our integrated model achieved a score of 51.08 on the navsim ICCV benchmark, securing third place.
Similar Papers
Scene-Adaptive Motion Planning with Explicit Mixture of Experts and Interaction-Oriented Optimization
Robotics
Helps self-driving cars navigate city streets safely.
Multi-Domain Enhanced Map-Free Trajectory Prediction with Selective Attention
CV and Pattern Recognition
Helps self-driving cars predict where others will go.
SAC-MoE: Reinforcement Learning with Mixture-of-Experts for Control of Hybrid Dynamical Systems with Uncertainty
Robotics
Teaches robots to move in new, tricky places.