Today we are joined by Alexandre Bayen, Director of the Institute for Transportation Studies and Professor at UC Berkeley.
With a background in control theory, Alexandre found the fields of robotics, machine learning, action optimization and many more all progressively merging and evolving at a rapid pace. This led to his current research in mixed-autonomy traffic to understand how the growing automation in self-driving vehicles can be used to improve mobility and optimization on a scale that greatly impacts the flow of traffic dynamics.
At last year's AWS re:Invent, Alexandre presented on the future of mixed-autonomy traffic and the two major revolutions he predicts will take place in the next 10-15 years. First, is a model-free world for vehicle planning and coordination, where deep reinforcement learning is predominantly used to learn via simulation. Second, is end-to-end pixel learning and working directly with renderings to gather inputs. Listen to this thought-provoking episode and hear Alexandre share his current research challenges, examples from his vast experience, and where he sees the immediate potential for the future of our transportation systems.