Agentic AI for Robot Control: Flexible but still Fragile

TL;DR

This paper presents an agentic AI system for robot control that uses language models for planning and execution across different platforms, demonstrating flexibility but also revealing significant fragility and sensitivity to prompts.

Contribution

The paper introduces a flexible, language model-based robot control architecture capable of operating across diverse platforms with minimal reconfiguration.

Findings

System works on indoor manipulation and agricultural navigation tasks.

Exhibits fragility with non-deterministic and suboptimal behaviors.

Transferability mainly requires updating prompts and skill interfaces.

Abstract

Recent work leverages the capabilities and commonsense priors of generative models for robot control. In this paper, we present an agentic control system in which a reasoning-capable language model plans and executes tasks by selecting and invoking robot skills within an iterative planner and executor loop. We deploy the system on two physical robot platforms in two settings: (i) tabletop grasping, placement, and box insertion in indoor mobile manipulation (Mobipick) and (ii) autonomous agricultural navigation and sensing (Valdemar). Both settings involve uncertainty, partial observability, sensor noise, and ambiguous natural-language commands. The system exposes structured introspection of its planning and decision process, reacts to exogenous events via explicit event checks, and supports operator interventions that modify or redirect ongoing execution. Across both platforms, our proof-of-concept experiments reveal substantial fragility, including non-deterministic suboptimal behavior, instruction-following errors, and high sensitivity to prompt specification. At the same time, the architecture is flexible: transfer to a different robot and task domain largely required updating the system prompt (domain model, affordances, and action catalogue) and re-binding the same tool interface to the platform-specific skill API.