A memory-guided LLM harness that calls a frozen VLA only for contact-rich phases lifts success to 82.4% on LIBERO-Pro, 55.4% on RoboCasa365, and 58.4% on RoboTwin C2R with no policy finetuning.
Chatgpt for robotics: Design principles and model abilities
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
This paper presents an experimental study regarding the use of OpenAI's ChatGPT for robotics applications. We outline a strategy that combines design principles for prompt engineering and the creation of a high-level function library which allows ChatGPT to adapt to different robotics tasks, simulators, and form factors. We focus our evaluations on the effectiveness of different prompt engineering techniques and dialog strategies towards the execution of various types of robotics tasks. We explore ChatGPT's ability to use free-form dialog, parse XML tags, and to synthesize code, in addition to the use of task-specific prompting functions and closed-loop reasoning through dialogues. Our study encompasses a range of tasks within the robotics domain, from basic logical, geometrical, and mathematical reasoning all the way to complex domains such as aerial navigation, manipulation, and embodied agents. We show that ChatGPT can be effective at solving several of such tasks, while allowing users to interact with it primarily via natural language instructions. In addition to these studies, we introduce an open-sourced research tool called PromptCraft, which contains a platform where researchers can collaboratively upload and vote on examples of good prompting schemes for robotics applications, as well as a sample robotics simulator with ChatGPT integration, making it easier for users to get started with using ChatGPT for robotics.
citation-role summary
background 2
citation-polarity summary
fields
cs.RO 5roles
background 2polarities
background 2representative citing papers
SPARK reaches 43.7% success on six LIBERO-PRO cells by LLM-generated typed behavior trees plus multi-prompt perception and recovery, more than doubling CaP-Agent0 and VLA baselines.
A protocol-driven multi-agent VLA system with visual verification and AugSmolVLA augmentation improves wet-lab robot execution over ACT, X-VLA, and SmolVLA on atomic, composite, and bimanual tasks.
An intent-driven Real2Sim framework uses VLMs for semantic task decomposition to identify missing physical parameters and generates reactive behavior trees to acquire them via contact-rich robotic interactions on a Franka Panda arm.
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.
citing papers explorer
-
Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
A memory-guided LLM harness that calls a frozen VLA only for contact-rich phases lifts success to 82.4% on LIBERO-Pro, 55.4% on RoboCasa365, and 58.4% on RoboTwin C2R with no policy finetuning.
-
Sequential Planning via Anchored Robotic Keypoints
SPARK reaches 43.7% success on six LIBERO-PRO cells by LLM-generated typed behavior trees plus multi-prompt perception and recovery, more than doubling CaP-Agent0 and VLA baselines.
-
BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation
A protocol-driven multi-agent VLA system with visual verification and AugSmolVLA augmentation improves wet-lab robot execution over ACT, X-VLA, and SmolVLA on atomic, composite, and bimanual tasks.
-
Real2Sim via Active Perception with Behavior Trees Automatically Generated by VLMs
An intent-driven Real2Sim framework uses VLMs for semantic task decomposition to identify missing physical parameters and generates reactive behavior trees to acquire them via contact-rich robotic interactions on a Franka Panda arm.
-
A Survey on Vision-Language-Action Models for Embodied AI
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.