TL;DR
This work constructs ROSDevEval, a specialized benchmark comprising 240 real-world ROS programming tasks, and conducts a comprehensive empirical study to evaluate four state-of-the-art LLMs alongside a specialized code assistant (GitHub Copilot), revealing a severe domain capability gap.
Programmable Logic Controllers (PLCs) are central to industrial automation, yet their programming remains largely manual and time-consuming. While Large Language Models (LLMs) excel at general-purpose code generation, their use in industrial control is limited by tight coupling with physical hardware, constrained I/O signals, and strict safety requirements. We propose a novel approach to PLC code generation that takes as input structured lists of sensors and actuators from electrical CAD tools, together with the required control functionality. The task is formulated as generating machine-specific control functions grounded in available signals, ensuring physical implementability. The system is based on a single LLM adapted through multi-stage fine-tuning and enhanced with Retrieval-Augmented Generation (RAG). Experiments on error detection, code fixing, and code generation show that fine-tuning significantly improves performance. RAG provides strong gains in error detection and code generation, while offering limited benefit for code fixing, highlighting its task-dependent effectiveness.
MaCoPlanner is presented, a task-planning framework built on knowledge compiled from equipment manuals that converts equipment manuals into a typed intermediate representation, retrieves task- and state-relevant evidence, and uses it to support plan generation.
This work adapts Hugging Face's SmolVLA for Universal Robots lightweight robots, and releases the open-source repository ROS2SmolVLA that implements an interface for ROS 2 to SmolVLA, and makes it applicable for industrial-grade hardware.
TuRTLe, a unified evaluation framework designed to systematically assess LLMs across key RTL generation tasks, is proposed, enabling a comprehensive assessment of LLM performance in syntax correctness, functional correctness, synthesis, PPA optimization, and exact line completion.
Synthesizing deployable robot behavior trees (BTs) from natural language (NL) requires grounding to ensure every generated BT references only skills a robot can actually execute. Existing LLM-based BT synthesis approaches often place this grounding responsibility on the prompt author. This makes deployment brittle when the author does not know which skills the robot can execute, how those skills are parameterized, or how the robot runtime software constrains valid BT structure. This paper proposes a contract-grounded BT synthesis architecture in which a coding agent queries a robot-side Model Context Protocol (MCP) server to retrieve an explicit contract consisting of a skill library, permitted BT operators, and optional BT composition templates, before synthesizing a BT for validation and execution. In our framework, non-expert operators issue NL commands without knowledge of robot implementation details, while a robot runtime validation gate enforces correctness before execution. We evaluate two LLMs, a closed model (Sonnet 4.6) and a smaller open-source model (Gemma4:31b), across 110 simulated tasks in PyRoboSim and 14 tasks on a physical Husarion Panther robot. Results show that contract grounding enables near-perfect BT validation and high task success, that BT composition templates substantially recover success on reactive control-flow tasks for the smaller model, and that the architecture transfers to physical hardware running a Nav2 stack opaque to both operator and agent.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
