6 papers
EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models
Zhikai Zhao, Chuanbo Hua, Federico Berto +4
Robot navigation is a crucial task with applications to social robots in dynamic human environments. While Reinforcement Learning (RL) has shown great promise for this problem, the…
JudgeFlow: Agentic Workflow Optimization via Block Judge
Zihan Ma, Zhikai Zhao, Chuanbo Hua +2
Optimizing LLM-based agentic workflows is challenging for scaling AI capabilities. Current methods rely on coarse, end-to-end evaluation signals and lack fine-grained signals on wh…
TrajEvo: Trajectory Prediction Heuristics Design via LLM-driven Evolution
Zhikai Zhao, Chuanbo Hua, Federico Berto +4
Trajectory prediction is a critical task in modeling human behavior, especially in safety-critical domains such as social robotics and autonomous vehicle navigation. Traditional he…
TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution
Zhikai Zhao, Chuanbo Hua, Federico Berto +4
Trajectory prediction is a crucial task in modeling human behavior, especially in fields as social robotics and autonomous vehicle navigation. Traditional heuristics based on handc…
USPR: Learning a Unified Solver for Profiled Routing
Chuanbo Hua, Federico Berto, Zhikai Zhao +3
The Profiled Vehicle Routing Problem (PVRP) extends the classical VRP by incorporating vehicle-client-specific preferences and constraints, reflecting real-world requirements such…
RRNCO: Towards Real-World Routing with Neural Combinatorial Optimization
Jiwoo Son, Zhikai Zhao, Federico Berto +4
The practical deployment of Neural Combinatorial Optimization (NCO) for Vehicle Routing Problems (VRPs) is hindered by a critical sim-to-real gap. This gap stems not only from trai…