Papers
7
Total Citations
91
H-Index
7
About
Lasse Peters is a robotics and autonomous systems researcher whose work sits at the intersection of game theory, motion planning, and multi-agent decision-making. His research addresses one of the central challenges in modern robotics: how autonomous agents, particularly intelligent vehicles, can reason about and interact with other agents whose intentions and objectives may be unknown or uncertain. Peters has made significant contributions to the theory and computation of differential games, developing efficient algorithms for solving nonlinear multi-player scenarios that were previously considered intractable. His 2020 work on iterative linear-quadratic approximations (20 citations) established practical methods for multi-agent planning, while his research on inference-based strategy alignment explored how agents can coordinate under coupled, competing objectives. More recently, his work on learning opponent objectives (21 citations) and contingency games (18 citations) has pushed the frontier toward more adaptive, uncertainty-aware autonomous systems capable of operating in unpredictable real-world environments. Beyond game-theoretic planning, Peters has also contributed to computer vision, applying genetic algorithms to neural network design for object detection. Collectively, his publications demonstrate a researcher who combines rigorous mathematical foundations with practical algorithmic innovation, making meaningful strides toward robots that can safely and intelligently navigate complex social interactions.
Research Focus
Key Achievements
Top Papers
- 1Learning to Play Trajectory Games Against Opponents With Unknown Objectives21 citations · 2023
- 2
- 3Contingency Games for Multi-Agent Interaction18 citations · 2024
- 4
- 5
- 6Inference-Based Strategy Alignment for General-Sum Differential Games8 citations · 2020
- 7Inference-Based Strategy Alignment for General-Sum Differential Games7 citations · 2020