Large Language Models Powered Context-Aware Motion Prediction

Motion prediction is among the most fundamental tasks in autonomous driving. Traditional methods of motion forecasting primarily encode vector information of maps and historical trajectory data of traffic participants, lacking a comprehensive understanding of overall traffic semantics, which in turn affects the performance of prediction tasks. In this paper, we utilized Large Language Models (LLMs) to enhance the global traffic context understanding for motion prediction tasks. We first conducted systematic prompt engineering, vi- sualizing complex traffic environments and historical trajec- tory information of traffic participants into image prompts— Transportation Context Map (TC-Map), accompanied by cor- responding text prompts. Through this approach, we obtained rich traffic context information from the LLM. By integrating this information into the motion prediction model, we demon- strate that such context can enhance the accuracy of motion predictions. Furthermore, considering the cost associated with LLMs, we propose a cost-effective deployment strategy: en- hancing the accuracy of motion prediction tasks at scale with 0.7% LLM-augmented datasets. Our research offers valuable insights into enhancing the understanding of traffic scenes of LLMs and the motion prediction performance of autonomous driving. The source code is available at https://github. com/AIR-DISCOVER/LLM-Augmented-MTR and https: //aistudio.baidu.com/projectdetail/7809548.