Project
The internship aims to develop a controller for a social mobile robot (ARI) to have a conversation with people using large language models (LLMs) such as ChatGPT. The internship is part of our European SPRING project. SPRING aims to develop mobile robots that will be employed in healthcare environments. The robots should communicate with patients, their families, and caretakers to inform, aid, and entertain them.
Task
During your internship, you will develop a controller (Python, ROS) for ARI, our social robot. The controller has the following tasks: 1) navigate towards a human (or group), 2) have a conversation with it (or them), and 3) leave the conversation. For this controller, you will use existing components from the SPRING project such as mapping and localization of the robot and humans, human-aware navigation, speech recognition, and a simple dialogue system based on ChatGPT.
Your task will be to combine these components to create a compelling behavior for the robot. Moreover, you will focus on investigating how to optimally use LLMs such as ChatGPT to have a natural and comfortable conversation with the robot, for example, by using prompt engineering [1].
You will have to compare different techniques and report your experimental results in a comprehensive manner in the form of a small research paper.
During the internship, you will have the chance to develop and implement your own ideas to improve the conversation with the robot, for example, by investigating gaze, gestures, or emotions.
Team
You will join RobotLearn, an international team of researchers and students at Inria Grenoble. Besides its research into robotics, the team has a strong background in audio-visual computation and its application to robotics. You will be supervised by Chris Reinke (Postdoc), Xavier Alameda-Pineda (head of the team), and our robotic engineers during your internship.
Requirements
Our main requirements are 1) motivation, 2) general knowledge of Machine Learning and Artificial Intelligence, and 3) knowledge of Python programming. Knowledge of robotics and natural language programming is NOT mandatory but a plus.
Conditions
The internship should start in the second half of 2023. It has a duration of 5 to 6 months. There will be a compensation of 500 – 600 Euro per month. Additionally, you will receive subsidized lunch meals (one lunch costs 2 – 4 Euro). You will have a dedicated working space at Inria and access to our social robotic platform.
Application
Please send an e-mail to chris.reinke@inria.fr including a paragraph about your motivation, your CV, and a recent transcript of your grades.
References
[1] White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., … & Schmidt, D. C. (2023). A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382.
