Max Robotics — Global Service Robot Directory + US Certification

About

Satomi Sugaya’s research lies at the intersection of robotics, deep learning, and motion planning, with a focus on enabling robots to navigate and operate safely in dynamic environments. Her most impactful contributions center on two key challenges: moving obstacle avoidance and swept volume estimation. In her highly cited 2019 work, Sugaya pioneered the use of deep reinforcement learning (RL) for moving obstacle avoidance, demonstrating that RL policies can simultaneously predict obstacle motion and generate avoidance actions directly from sensor data—outperforming traditional formal methods. This work has garnered 14 citations and established a new paradigm for reactive robot navigation. She is perhaps best known for her groundbreaking series of papers on deep swept volume estimation (2020), which collectively earned over 30 citations. By training deep neural networks to rapidly approximate the swept volume of multi-link robots, Sugaya solved a decades-old computational bottleneck in task and motion planning, making real-time swept volume computation feasible for the first time. Her innovative use of transfer learning across different robot geometries further extends the practicality of her methods. Sugaya’s work has been recognized for its potential to transform how robots plan motions in cluttered, unpredictable spaces—a critical capability for applications ranging from manufacturing to autonomous driving.