Max Robotics — Global Service Robot Directory + US Certification

About

Rachel Gehlhar is a leading researcher at the intersection of robotic locomotion, assistive devices, and nonlinear control theory. Her work focuses on developing rigorous, model-based control frameworks for lower-limb prostheses, with the goal of translating bipedal robotic walking methods to improve mobility for individuals with amputations. In her highly cited 2019 paper (24 citations), she pioneered the experimental implementation of adaptive and robust adaptive controllers for transfemoral prostheses, marking a critical step toward reliable, model-based prosthetic control. She further advanced the field by introducing musculoskeletal models into hybrid zero dynamics to generate natural, multicontact walking gaits for robotic assistive devices (2022, 14 citations). Gehlhar also developed separable control Lyapunov functions (2020, 12 citations), enabling prosthesis controllers that rely only on locally available sensor data while guaranteeing stability—a key innovation for practical deployment. Her work with recurrent neural network control and the EdgeDRNN accelerator (2020, 12 citations) represents an early effort to embed learning-based controllers into prosthetic hardware. Through these contributions, Gehlhar is shaping a future where amputees can walk more naturally and efficiently with intelligent, adaptive prosthetic limbs.