Bruno Brito
Papers
16
Total Citations
597
H-Index
12
About
Bruno Brito is a leading researcher in autonomous robotics, specializing in motion planning and navigation for dynamic, human-populated environments. His work centers on developing optimization-based and learning-driven methods that enable robots to safely and efficiently interact with moving obstacles, including humans and other robots. Brito’s most impactful contribution is his model predictive contouring control approach for collision avoidance, which has garnered 197 citations by providing a real-time, receding-horizon solution for unstructured settings. He has further advanced decentralized multi-robot systems with interaction-aware trajectory predictions (70 citations) and probabilistic collision avoidance using buffered uncertainty-aware Voronoi cells (57 citations), addressing the critical challenge of predicting and reacting to uncertain agent behaviors. Brito also explores learning-based subgoal and viewpoint recommendations for navigation and information gathering, as well as whole-body trajectory optimization for mobile manipulators. His work on scenario-based trajectory optimization under uncertainty (29 citations) and self-supervised continual learning for pedestrian prediction (14 citations) demonstrates a commitment to robust, adaptive systems. With over 550 total citations, Brito’s research is pivotal for deploying autonomous robots in warehouses, retail, and urban environments, bridging the gap between theoretical planning and real-world social compliance.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7Towards Automated Order Picking Robots for Warehouses and Retail32 citations · 2019
- 8Scenario-Based Trajectory Optimization in Uncertain Dynamic Environments29 citations · 2021
- 9
- 10