DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling

Abstract

Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems. While existing approaches may sample from a predicted distribution of vehicle trajectories, they lack the ability to explore it -- a key ability for evaluating safety from a planning and verification perspective. In this work, we devise a novel approach for generating realistic and diverse vehicle trajectories. We extend the generative adversarial network (GAN) framework with a low-dimensional approximate semantic space, and shape that space to capture semantics such as merging and turning. We sample from this space in a way that mimics the predicted distribution, but allows us to control coverage of semantically distinct outcomes. We validate our approach on a publicly available dataset and show results that achieve state-of-the-art prediction performance, while providing improved coverage of the space of predicted trajectory semantics.

arXiv comment8 pages, 5 figures, 1 table

References in corpus (16)

• Better Mixing via Deep Representations
• Argoverse: 3D Tracking and Forecasting with Rich Maps
• MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
• Diversity-Sensitive Conditional Generative Adversarial Networks
• Multiple Futures Prediction
• Diverse Trajectory Forecasting with Determinantal Point Processes
• DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
• Interpreting the Latent Space of GANs for Semantic Face Editing
• Probabilistic Vehicle Trajectory Prediction over Occupancy Grid Map via Recurrent Neural Network
• Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
• A non-parametric k-nearest neighbour entropy estimator
• Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
• Learning Self-Imitating Diverse Policies
• Conditional Generative Neural System for Probabilistic Trajectory Prediction
• Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning
• Disentangled Relational Representations for Explaining and Learning from Demonstration

Cited by in corpus (3)

• LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving
• Learning Lane Graph Representations for Motion Forecasting
• Fast Risk Assessment for Autonomous Vehicles Using Learned Models of Agent Futures