π\mathbf{R}^2: Reactive Real-time Flow Policies
Making robot control policies react fast enough to handle the unexpected
Current AI-powered robot controllers plan their moves in chunks and can't adjust mid-action, making them clumsy when things change unexpectedly. Researchers created πR², a new approach that lets robots react to what they sense right now while keeping powerful AI models and planning for multiple actions at once. On real robots, it replans about 4 times faster than existing methods and improves success rates by up to 30%.
Robots trained with large AI models are increasingly useful, but they've been slow to react to surprises—a dropped object, a shifting surface, an unexpected obstacle. πR² lets them adjust course in real-time without slowing down, using the same powerful models. This means robots could handle messier, less predictable real-world tasks like assembly lines or warehouse work where conditions constantly shift.