Closed-loop Multi-step Planning

2024-02-23

AI Summary

Existing robotic systems predominantly rely on open-loop preprogramming or single-step reactive behaviors, limiting their ability to autonomously generate and execute multi-step, complex actions in dynamic environments. Method: We propose a fully closed-loop, perception-driven hierarchical planning framework that abstracts tasks as discrete, transient closed-loop controllers (“Tasks”). Integrating physics-inspired causal environmental modeling with task-level sequential planning, the framework enables online generation, simulation, and execution of multi-step task chains. Contribution: This work represents the first integration of closed-loop control with hierarchical causal reasoning, eliminating dependence on open-loop priors. We validate the approach end-to-end on two real-world robotic platforms, demonstrating robust multi-step behavioral generation and execution solely from closed-loop sensory inputs. Experimental results confirm both functional efficacy and operational robustness under realistic dynamic conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Living organisms interact with their surroundings in a closed-loop fashion, where sensory inputs dictate the initiation and termination of behaviours. Even simple animals are able to develop and execute complex plans, which has not yet been replicated in robotics using pure closed-loop input control. We propose a solution to this problem by defining a set of discrete and temporary closed-loop controllers, called ``Tasks'', each representing a closed-loop behaviour. We further introduce a supervisory module which has an innate understanding of physics and causality, through which it can simulate the execution of Task sequences over time and store the results in a model of the environment. On the basis of this model, plans can be made by chaining temporary closed-loop controllers. Our proposed framework was implemented for a real robot and tested in two scenarios as proof of concept.

Problem

• Robot Adaptability
• Complex Planning
• Environmental Response

Innovation

• Decomposed Planning
• Causal Understanding
• Adaptive Robotics