Interpretable and Flexible Target-Conditioned Neural Planners For Autonomous Vehicles
arXiv:2309.13485 · doi:10.1109/ICRA48891.2023.10160913
Abstract
Learning-based approaches to autonomous vehicle planners have the potential to scale to many complicated real-world driving scenarios by leveraging huge amounts of driver demonstrations. However, prior work only learns to estimate a single planning trajectory, while there may be multiple acceptable plans in real-world scenarios. To solve the problem, we propose an interpretable neural planner to regress a heatmap, which effectively represents multiple potential goals in the bird's-eye view of an autonomous vehicle. The planner employs an adaptive Gaussian kernel and relaxed hourglass loss to better capture the uncertainty of planning problems. We also use a negative Gaussian kernel to add supervision to the heatmap regression, enabling the model to learn collision avoidance effectively. Our systematic evaluation on the Lyft Open Dataset across a diverse range of real-world driving scenarios shows that our model achieves a safer and more flexible driving performance than prior works.
References in corpus (9)
- A systematic study of the class imbalance problem in convolutional neural networks
- A Survey of Autonomous Driving: Common Practices and Emerging Technologies
- How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
- TNT: Target-driveN Trajectory Prediction
- One Thousand and One Hours: Self-driving Motion Prediction Dataset
- Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
- Numerical Coordinate Regression with Convolutional Neural Networks
- Unifying Voxel-based Representation with Transformer for 3D Object Detection
- Exploring Imitation Learning for Autonomous Driving with Feedback Synthesizer and Differentiable Rasterization