Exploring Dynamic Context for Multi-path Trajectory Prediction

To accurately predict future positions of different agents in traffic scenarios is crucial for safely deploying intelligent autonomous systems in the real-world environment. However, it remains a challenge due to the behavior of a target agent being affected by other agents dynamically and there being more than one socially possible paths the agent could take. In this paper, we propose a novel framework, named Dynamic Context Encoder Network (DCENet). In our framework, first, the spatial context between agents is explored by using self-attention architectures. Then, the two-stream encoders are trained to learn temporal context between steps by taking the respective observed trajectories and the extracted dynamic spatial context as input. The spatial-temporal context is encoded into a latent space using a Conditional Variational Auto-Encoder (CVAE) module. Finally, a set of future trajectories for each agent is predicted conditioned on the learned spatial-temporal context by sampling from the latent space, repeatedly. DCENet is evaluated on one of the most popular challenging benchmarks for trajectory forecasting Trajnet and reports a new state-of-the-art performance. It also demonstrates superior performance evaluated on the benchmark inD for mixed traffic at intersections. A series of ablation studies is conducted to validate the effectiveness of each proposed module. Our code is available at https://github.com/wtliao/DCENet.

Authors

• Hao Cheng 0008
• Wentong Liao
• Xuejiao Tang
• Michael Ying Yang
• Monika Sester
• Bodo Rosenhahn

Keywords

• Codes
• Automation
• Autonomous systems
• Conferences
• Layout
• Benchmark testing
• Trajectory
• Trajectory Prediction
• Benchmark
• Superior Performance
• Latent Space
• Spatial Context
• Real-world Environments
• Future Trajectories
• Targeting Agents
• Traffic Scenarios
• Trajectories Of Agents
• Conditional Variational Autoencoder
• Transformer
• Convolutional Neural Network
• Latent Variables
• Dynamic Interactions
• Long Short-term Memory
• Recurrent Neural Network
• Functional Dynamics
• Fully-connected Layer
• Multiple Trajectories
• Multiple Predictors
• Self-attention Module
• Layer Orientation
• Heterogeneous Agents
• Pedestrian Walking
• Low Stream
• Ranking Method
• Global Average Pooling
• Self-attention Layer