Integrating Vision Foundation Models with Reinforcement Learning for Enhanced Object Interaction
This work addresses the challenge of improving robotic perception and interaction for autonomous agents in simulated indoor settings, representing an incremental advancement by combining existing models.
The paper tackled the problem of enhancing object interaction in simulated environments by integrating vision foundation models with reinforcement learning, resulting in a 68% increase in cumulative reward, a 52.5% improvement in interaction success rate, and a 33% boost in navigation efficiency.
This paper presents a novel approach that integrates vision foundation models with reinforcement learning to enhance object interaction capabilities in simulated environments. By combining the Segment Anything Model (SAM) and YOLOv5 with a Proximal Policy Optimization (PPO) agent operating in the AI2-THOR simulation environment, we enable the agent to perceive and interact with objects more effectively. Our comprehensive experiments, conducted across four diverse indoor kitchen settings, demonstrate significant improvements in object interaction success rates and navigation efficiency compared to a baseline agent without advanced perception. The results show a 68% increase in average cumulative reward, a 52.5% improvement in object interaction success rate, and a 33% increase in navigation efficiency. These findings highlight the potential of integrating foundation models with reinforcement learning for complex robotic tasks, paving the way for more sophisticated and capable autonomous agents.