General Dynamic Goal Recognition

2025/05/14 by Elhadad, Osher, Mirsky, Reuth · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2505.09737

Abstract

Understanding an agent's intent through its behavior is essential in human-robot interaction, interactive AI systems, and multi-agent collaborations. This task, known as Goal Recognition (GR), poses significant challenges in dynamic environments where goals are numerous and constantly evolving. Traditional GR methods, designed for a predefined set of goals, often struggle to adapt to these dynamic scenarios. To address this limitation, we introduce the General Dynamic GR problem - a broader definition of GR - aimed at enabling real-time GR systems and fostering further research in this area. Expanding on this foundation, this paper employs a model-free goal-conditioned RL approach to enable fast adaptation for GR across various changing tasks.

Citations

• Goal Recognition using Actor-Critic Optimization
• ODGR: Online Dynamic Goal Recognition
• Real-time goal recognition using approximations in Euclidean space
• Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
• Goal Recognition as a Deep Learning Task: the GRNet Approach
• Goal-Conditioned Reinforcement Learning: Problems and Solutions
• panda-gym: Open-source goal-conditioned environments for robotic learning
• learn2learn: A Library for Meta-Learning Research
• Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction
• A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Intent Recognition in Smart Living Through Deep Recurrent Neural Networks
• Trust Region Policy Optimization
• Gymnasium: A Standard Interface for Reinforcement Learning Environments
• Reinforcement Learning: An Introduction

Cited by

• Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates
• GRAML: Goal Recognition As Metric Learning

Related

• ODGR: Online Dynamic Goal Recognition
• Active Goal Recognition
• Online Dynamic Goal Recognition in Gym Environments
• Goal Recognition Design for General Behavioral Agents using Machine Learning
• Investigating the Combination of Planning-Based and Data-Driven Methods for Goal Recognition