Papers
10
Total Citations
225
H-Index
9
About
Sabrina M. Neuman is a pioneering researcher at the intersection of computer architecture and robotics, whose work focuses on designing specialized hardware accelerators to meet the demanding computational requirements of autonomous robotic systems. Her landmark contribution, "Robomorphic Computing" (2021, 42 citations), introduced a transformative design methodology that parameterizes domain-specific accelerators according to a robot's physical morphology, directly addressing the critical performance gap in real-time motion planning and control. Building on this foundation, she has advanced GPU, CPU, and FPGA acceleration of robot dynamics gradients, developed the GRiD library for GPU-accelerated rigid body dynamics, and created RoboShape, a scalable framework for deploying accelerators across diverse robotic platforms. Neuman has also championed accessibility in robotics computing through open-source tools like RobotCore and RobotPerf, lowering barriers for hardware acceleration within the ROS 2 ecosystem. Her influential work on "Tiny Robot Learning" (2022, 38 citations) highlights her broader vision of deploying machine learning on severely resource-constrained robots. With over 225 cumulative citations spanning hardware design, dynamics algorithms, and autonomous aerial systems, Neuman's research is reshaping how the robotics community thinks about computation, making intelligent autonomy faster, more efficient, and widely deployable.
Research Focus
Key Achievements
Top Papers
- 1
- 2Accelerating Robot Dynamics Gradients on a CPU, GPU, and FPGA39 citations · 2021
- 3
- 4
- 5RobotCore: An Open Architecture for Hardware Acceleration in ROS 222 citations · 2022
- 6
- 7Benchmarking and Workload Analysis of Robot Dynamics Algorithms16 citations · 2019
- 8GRiD: GPU-Accelerated Rigid Body Dynamics with Analytical Gradients14 citations · 2022
- 9
- 10