Autonomous Systems
-
ReVLA@ICRA: Visual Robustness for Robotic Foundation Models
We have presented ReVLA, our first work at ICRA 2025 in Atlanta.
-
Learnable Online Graph Representations for 3D Multi-Object Tracking
An online 3D Multi-Object Tracking method based on graph neural networks.
-
Decoder fusion RNN: Context and interaction aware decoders for trajectory prediction
A multi-headed attention based method for vehicle trajectory prediction using map data encoded on a graph.
-
Action sequence predictions of vehicles in urban environments using map and social context
Views the traffic agent trajectory prediction task form a classification perspective and proposes a method to automatically annotate trajectory data by using graph-based maps.
-
Learning to avoid poor images: Towards task-aware C-arm cone-beam CT trajectories
A robotic CBCT system that that predicts an acquisition trajectory optimized online during a scan.