Dean Egerstedt will welcome the attendees and provide a Keynote Lecture: 

Robot Design for Long-Duration Autonomy. 

Abstract:   When robots are to be deployed over long time scales, optimality should take a backseat to “survivability,” i.e., it is more important that the robots do not break or completely deplete their energy sources than that they perform certain tasks as effectively as possible. In this talk, we consider this question of long duration autonomy for teams of robots that are deployed over a sustained period of time and that can be recruited to perform a number of different tasks in a distributed, safe and provably correct manner. This development will introduce novel representations of task and safety constraints, as well as a detour into ecology as a way of understanding how persistent environmental monitoring can be achieved by studying animals with low-energy life-styles, such as the three-toed sloth.

Prof. Larochelle will provide Keynote Lecture 2:

Just when we thought we had engineering education all figured out, along came AI. Now what?

Abstract: In recent years, the growth in scholarship in engineering education research has been experiencing tremendous growth. Doctoral programs in engineering education have been established at several leading engineering colleges. Engineering educators had been making great strides in pedagogy and assessment of learning in engineering education. Active learning techniques, such as project-based learning, became commonplace. Then in the post COVID-19 world, generative large language model artificial intelligence (AI) tools exploded in both accessibility and capability. Today, the disruption of AI to the practice of engineering is forcing engineering educators to rapidly adapt and question their teaching methods and their efficacy. In this talk, we’ll explore the role of AI in engineering education and discuss how it aligns with, and can support, the various levels in Bloom’s taxonomy of the cognitive domain.

Prof. Su will provide a Hands-on Workshop: 

The Use of AI in Kinematics

Abstract:  The study of kinematics lies at the heart of mechanism design and robotics, fundamentally involving the formulation and solution of algebraic equations. Traditionally, deriving analytical solutions and implementing them in code has been both time-intensive and technically demanding. With the rapid advancement of large language models (LLMs), we now have powerful new tools capable of reasoning symbolically, assisting with algebraic manipulation, and generating executable code in real time.  These capabilities open new possibilities for accelerating research and enhancing education in kinematics. 

In this workshop, I will demonstrate practical, hands-on approaches to using AI tools for solving representative problems in robot kinematics. Examples will include positional analysis of planar, spherical, and spatial mechanisms, as well as kinematic synthesis of planar four-bar linkages. Participants will also see how these AI-driven workflows can be extended to create simple interactive applications, and how to leverage AI for generating and organizing code repositories on GitHub for teaching, research, and dissemination of results. By integrating AI into the practice of kinematics, researchers and educators can not only streamline the process of algebraic problem solving and coding but also empower students with intuitive, accessible computational tools.