Improving Movement Predictions of Traffic Actors in Bird's-Eye View Models using GANs and Differentiable Trajectory Rasterization
arXiv:2004.06247
Abstract
One of the most critical pieces of the self-driving puzzle is the task of predicting future movement of surrounding traffic actors, which allows the autonomous vehicle to safely and effectively plan its future route in a complex world. Recently, a number of algorithms have been proposed to address this important problem, spurred by a growing interest of researchers from both industry and academia. Methods based on top-down scene rasterization on one side and Generative Adversarial Networks (GANs) on the other have shown to be particularly successful, obtaining state-of-the-art accuracies on the task of traffic movement prediction. In this paper we build upon these two directions and propose a raster-based conditional GAN architecture, powered by a novel differentiable rasterizer module at the input of the conditional discriminator that maps generated trajectories into the raster space in a differentiable manner. This simplifies the task for the discriminator as trajectories that are not scene-compliant are easier to discern, and allows the gradients to flow back forcing the generator to output better, more realistic trajectories. We evaluated the proposed method on a large-scale, real-world data set, showing that it outperforms state-of-the-art GAN-based baselines.
arXiv commentAccepted for publication at ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2020
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Improved Training of Wasserstein GANs
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
- Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
- MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
- Adversarial Feature Matching for Text Generation
- Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
- Towards Diverse and Natural Image Descriptions via a Conditional GAN
- Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving
- Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions
- Deep Kinematic Models for Kinematically Feasible Vehicle Trajectory Predictions