Related papers: RobotGPT: Robot Manipulation Learning from ChatGPT
ChatGPT has been increasingly used in computer science, offering efficient support across software development tasks. While it helps students navigate programming challenges, its use also raises concerns about academic integrity and…
This paper investigates the dynamics of human AI collaboration in software engineering, focusing on the use of ChatGPT. Through a thematic analysis of a hands on workshop in which 22 professional software engineers collaborated for three…
This paper proposes a framework for quantitatively evaluating interactive LLMs such as ChatGPT using publicly available data sets. We carry out an extensive technical evaluation of ChatGPT using 23 data sets covering 8 different common NLP…
Prior research shows that how students engage with Large Language Models (LLMs) influences their problem-solving and understanding, reinforcing the need to support productive LLM-uses that promote learning. This study evaluates the impact…
Recently, the ChatGPT LLM has received great attention: it can be used as a bot for discussing source code, prompting it to suggest changes, provide descriptions or even generate code. Typical demonstrations generally focus on existing…
Robot simulation has been an essential tool for data-driven manipulation tasks. However, most existing simulation frameworks lack either efficient and accurate models of physical interactions with tactile sensors or realistic tactile…
Delivering personalised, formative feedback to multiple problem-based learning groups in a short time period can be almost impossible. We employed ChatGPT to provide personalised formative feedback in a one-hour Zoom break-out room activity…
There has been a recent explosion of research on Large Language Models (LLMs) for software engineering tasks, in particular code generation. However, results from LLMs can be highly unstable; nondeterministically returning very different…
Current robots are capable of computing plans to accomplish complex tasks. However, real-world environments are inherently open and dynamic, and unforeseen situations frequently arise during plan execution, such as jamming doors and fallen…
OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) and revolutionized the approach in artificial intelligence to human-model interaction. Several publications on ChatGPT evaluation test its effectiveness on well-known…
ChatGPT disrupted the application of machine-learning methods and drastically reduced the usage barrier. Chatbots are now widely used in a lot of different situations. They provide advice, assist in writing source code, or assess and…
Recent studies have highlighted the limitations of large language models in mathematical reasoning, particularly their inability to capture the underlying logic. Inspired by meta-learning, we propose that models should acquire not only…
We use prompt engineering to guide ChatGPT in the automation of text mining of metal-organic frameworks (MOFs) synthesis conditions from diverse formats and styles of the scientific literature. This effectively mitigates ChatGPT's tendency…
We study a human-robot collaborative transportation task in presence of obstacles. The task for each agent is to carry a rigid object to a common target position, while safely avoiding obstacles and satisfying the compliance and actuation…
ChatGPT is not only fun to chat with, but it also searches information, answers questions, and gives advice. With consistent moral advice, it might improve the moral judgment and decisions of users, who often hold contradictory moral…
Many language-guided robotic systems rely on collapsing spatial reasoning into discrete points, making them brittle to perceptual noise and semantic ambiguity. To address this challenge, we propose RoboMAP, a framework that represents…
High-level robot skills represent an increasingly popular paradigm in robot programming. However, configuring the skills' parameters for a specific task remains a manual and time-consuming endeavor. Existing approaches for learning or…
The increasing volume of log data produced by software-intensive systems makes it impractical to analyze them manually. Many deep learning-based methods have been proposed for log-based anomaly detection. These methods face several…
Evaluating learned robot control policies to determine their physical task-level capabilities costs experimenter time and effort. The growing number of policies and tasks exacerbates this issue. It is impractical to test every policy on…
In this paper, we present an approach for quantifying the propagated uncertainty of robot systems in an online and data-driven manner. Especially in Human-Robot Collaboration, keeping track of the safety compliance during run time is…