Search Results for author:
Found 10 papers, 6 papers with code
Scaling Self-Supervised End-to-End Driving with Multi-View Attention Learning
With only self-supervised training data, our model yields almost expert performance in CARLA's Nocrash metrics and could be rival to the SOTA models requiring large amounts of human labeled data.
Learned Image Compression for Machine Perception
Compression that ensures high accuracy on computer vision tasks such as image segmentation, classification, and detection therefore has the potential for significant impact across a wide variety of settings.
Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction
AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene.
Action-Based Representation Learning for Autonomous Driving
Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems.
Multimodal End-to-End Autonomous Driving
On the other hand, we find end-to-end driving approaches that try to learn a direct mapping from input raw sensor data to vehicle control signals.
Exploring the Limitations of Behavior Cloning for Autonomous Driving
Driving requires reacting to a wide variety of complex environment conditions and agent behaviors.
Ranked #13 on
Autonomous Driving
on CARLA Leaderboard
On Offline Evaluation of Vision-based Driving Models
We show that the correlation of offline evaluation with driving quality can be significantly improved by selecting an appropriate validation dataset and suitable offline metrics.
CARLA: An Open Urban Driving Simulator
We introduce CARLA, an open-source simulator for autonomous driving research.
End-to-end Driving via Conditional Imitation Learning
However, driving policies trained via imitation learning cannot be controlled at test time.
Single Image Restoration for Participating Media Based on Prior Fusion
Differently from the related work that only deal with a medium, we obtain generality by using an image formation model and a fusion of new image priors.
