Stepwise Goal-Driven Networks for Trajectory Prediction

Abstract

We propose to predict the future trajectories of observed agents (e.g., pedestrians or vehicles) by estimating and using their goals at multiple time scales. We argue that the goal of a moving agent may change over time, and modeling goals continuously provides more accurate and detailed information for future trajectory estimation. To this end, we present a recurrent network for trajectory prediction, called Stepwise Goal-Driven Network (SGNet). Unlike prior work that models only a single, long-term goal, SGNet estimates and uses goals at multiple temporal scales. In particular, it incorporates an encoder that captures historical information, a stepwise goal estimator that predicts successive goals into the future, and a decoder that predicts future trajectory. We evaluate our model on three first-person traffic datasets (HEV-I, JAAD, and PIE) as well as on three bird's eye view datasets (NuScenes, ETH, and UCY), and show that our model achieves state-of-the-art results on all datasets. Code has been made available at: https://github.com/ChuhuaW/SGNet.pytorch.

Accepted By RA-L and ICRA2022

References in corpus (5)

• TNT: Target-driveN Trajectory Prediction
• Argoverse: 3D Tracking and Forecasting with Rich Maps
• SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
• LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion
• Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians

Cited by in corpus (4)

• SocialVAE: Human Trajectory Prediction using Timewise Latents
• THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling
• Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning
• Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals