SUN, JIAWEI (National University of Singapore), YUAN, CHENGRAN (National University of Singapore), SUN, Shuo (National University of Singapore), Shanze, Wang (National University of Singapore), Han, Yuhang (National University of Singapore), Ma, Shuailei (Northeastern University China), Huang, Zefan (National University of Singapore), Wong, Chern Yuen Anthony (MooVita Pte Ltd), Tee, Keng Peng (Moovita), Ang Jr, Marcelo H (National University of Singapore)

ControlMTR: Control-Guided Motion Transformer with Scene-Compliant Intention Points for Feasible Motion Prediction

Scheduled for presentation during the Invited Session "Learning-powered and Knowledge-driven Autonomous Driving I" (ThAT1), Thursday, September 26, 2024, 10:30−10:50, Salon 1

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 14, 2024

Abstract

The ability to accurately predict feasible multi-modal future trajectories of surrounding traffic participants is crucial for behavior planning in autonomous vehicles. The Motion Transformer (MTR), a state-of-the-art motion prediction method, alleviated mode collapse and instability during training and enhanced overall prediction performance by replacing conventional dense future endpoints with a small set of fixed prior motion intention points. However, the fixed prior intention points make the MTR multi-modal prediction distribution over-scattered and infeasible in many scenarios. In this paper, we propose the ControlMTR framework to tackle the aforementioned issues by generating scene-compliant intention points and additionally predicting driving control commands, which are then converted into trajectories by a simple kinematic model with soft constraints. These control-generated trajectories will guide the directly predicted trajectories by an auxiliary loss function. Together with our proposed scene-compliant intention points, they can effectively restrict the prediction distribution within the road boundaries and suppress infeasible off-road predictions while enhancing prediction performance. Remarkably, without resorting to additional model ensemble techniques, our method surpasses the baseline MTR model across all performance metrics, achieving notable improvements of 5.22% in SoftmAP and a 4.15% reduction in MissRate. Our approach notably results in a 41.51% reduction in the cross-boundary rate of the MTR, effectively ensuring that the prediction distribution is confined within the drivable area.