We are delighted to announce that Professor Vijay Janapa Reddi from Harvard University has joined Acceleration Robotics Board of Advisors.
Professor Vijay Janapa Reddi is an associate professor of engineering and applied sciences at Harvard University. His research interests include machine learning, robotics, and the design of computer systems. He is an expert in low-power, high-performance system-on-chip (SoC) architectures, which he achieves by blending hardware and software via co-design in a unique manner. His long-term objective is to create open-source SoCs for robotics in order to commoditize the technology. Vijay leads a team of computer system architects at Harvard's Edge Computing Lab. He has contributed to the creation of industry benchmarks, such as MLPerf, and non-profit organizations, such as MLCommons, to allow global access to cutting-edge technology.
The collaboration with Vijay and his team started back in 2021, while discussing thoughts about how to create an Open Architecture for Hardware Acceleration in ROS 2. These initial ideas translated into a joint publication[1] that has a growing community around it, that has also been featured in ROSCon and IROS 2022 robotics conferences and later helped shape the architecture of our ROBOTCORE® Framework, an FPGA and GPU hardware acceleration framework for ROS.
Vijay and us share a common vision about robotics. How it is changing rapidly and how it must be studied with real examples and measurements on real robotic computations, rather than simply as a collection of definitions, designs, and marketing actions. We both believe that the quantitative approach to robotics systems architecture fits well in this context and helps robotic architects come up with better performing robots through an empirical strategy. Formally adding Vijay to our Board of Advisors will allow us to leverage his expertise and cooperate closely on new compute architectures for robots and in the creation of future robotics industry benchmarks to drive the design of high-performance computing for robots built on ROS 2.
Please join us in welcoming Vijay to Acceleration Robotics!
Mayoral-Vilches, V., Neuman, S.M., Plancher, B. and Reddi, V.J., 2022. RobotCore: An Open Architecture for Hardware Acceleration in ROS 2. arXiv preprint arXiv:2205.03929. ↩︎