Vehicle detection, tracking and motion forecasting are critical for intelligent vehicle sensing system. In this paper, we propose a single-stage deep neural network (DNN) called TAPNet, which combines consecutive frames of LiDAR scans and high-definition (HD) maps to jointly reason about Bird's Eye View (BEV) detection and trajectory prediction of vehicles. In our proposed method, an auxiliary past learning task is developed which can guide the backbone to exploit temporal information from training data by learning the motion history of vehicles. Moreover, We introduce a novel incremental trajectory loss function that can reduce the regressing varience and generate smooth trajectories. Experimental results on large-scale public dataset show that our proposed TAPNet outperforms other state-of-the-art models that jointly reason about BEV detection and motion forecasting.
TAPNet: Enhancing Trajectory Prediction with Auxiliary Past Learning Task
11.07.2021
4145917 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
TAPNET: ENHANCING TRAJECTORY PREDICTION WITH AUXILIARY PAST LEARNING TASK
British Library Conference Proceedings | 2021
|Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Prediction
ArXiv | 2024
|Enhancing Pedestrian Trajectory Prediction with Crowd Trip Information
ArXiv | 2024
|