3

MP3: A Unified Model to Map, Perceive, Predict and Plan

_CVPR 2021_ __(Best Paper Candidate, Oral)__ Interpretable end-to-end neural motion planning without high-definition maps

LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving

_ICCV 2021_ Contingency planning from diverse joint trajectory samples for all actors in the scene

Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes

_arXiv preprint 2021_ Cost-aware active learning allows for fine-grained selection of examples through partially labeled scenes

AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles

_CVPR 2021_ Critical scenario generation by modifying the actors' trajectories in a physically plausible manner and updating the LiDAR sensor data to create realistic observations of the perturbed world

Deep Multi-Task Learning for Joint Localization, Perception, and Prediction

_CVPR 2021_ Efficient end-to-end joint localization, perception, prediction able to correct localization errors

Diverse Complexity Measures for Dataset Curation in Self-driving

_IROS 2021_ Model-agnostic approach to dataset curation for autonomy tasks

Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting

_IROS 2021_ Hybrid instance-based and instance-free approach to pedestrian behavior prediction