RAX: A Framework for Autonomous Robot Exploration and Skill Acquisition

Researchers from Harvard, NVIDIA, UC Berkeley, MIT, and Stanford introduce RAX, an open-source framework that allows robot agents to autonomously explore and learn by converting effective interactions into executable code. RAX enables robots to perform complex tasks like opening an air fryer, using multi-modal perception, planning, and continuous learning without human intervention. The framework demonstrates strong performance across multiple simulation benchmarks, with an average improvement of 37.4% over existing baselines.