We want the self-driving robot to understand human language, such as "Find me a parking spot close to that red building." This involves building a good scene graph representation of the environment, connecting language with scene representation, and handling abstraction and ambiguity in human language.
- Strong programming
- Strong communication, collaboration, organization, and planning
- Proactive and fast self-learner
- Familiarity with language models and visual language models (Online and offline ones)
- Familiarity with machine learning: PyTorch
- Familiarity with software: ROS2, Python, C++, Linux, Bash, Git
- Learn and strengthen the skills above
- Understand the full pipeline required to develop an intelligent robot from start to finish
- Working with senior students and faculty advisors
Not a hard limit. We care more about talent and potential.