Research Projects

We leverage fundamental computer vision principles and deep learning to advance automotive perception in the task of 3D object detection - the task of estimating the six degrees of freedom pose and dimensions of objects of interest.

3D multi-object tracking is a key problem for autonomous vehicles, required to perform well-informed motion planning in dynamic environments. Particularly for densely occupied scenes, associating existing tracks to new detections remains challenging as existing systems tend to omit critical contextual information

Object-level pose estimation plays a key role in SLAM. The reliable object pose estimation can provide valuable information in many down-stream robotic applications (e.g., robot manipulation,  navigation and autonomous driving).

Motion prediction is a crucial component in autonomous driving that enables self-driving vehicles to forecast where other road users (vehicles, pedestrians, cyclists) might be in the next few seconds, helping to ensure safe and reliable navigation.

End-to-end autonomous driving is a fully differentiable system that processes raw sensor data directly into driving actions or trajectories, eliminating traditional modular components in favor of a unified, jointly-optimized neural network

Open-world navigation enables autonomous robots and vehicles to operate in diverse, unpredictable environments beyond pre-mapped domains. By leveraging multimodal sensor data and adaptive learning, these systems plan robust routes, handle unseen scenarios, and act without relying on dense prior maps or hand-crafted rules—advancing flexible, truly autonomous mobility.

UAV/UGV teams show strong promise for a range of applications, thanks to their complementary capabilities of maneuverability and endurance. In this project, we demonstrate some of the first automated docking of drones on moving ground vehicles, and push the state of the art in quadrotor aerodynamic modeling, pose estimation, and precision control.