Designing safe and reliable robotic assistance for caregiving is a grand challenge in robotics. A sixth of the United States population is over the age of 65 and in 2014 more than a quarter of the population had a disability. Robotic caregivers could positively benefit society; yet, physical robotic assistance presents several challenges and open research questions relating to accessible interfaces, autonomous control, and multimodal sensing and learning. In this talk, I will present recent techniques and technology that my group has developed towards addressing core challenges in robotic caregiving. First, I will introduce inertial and high-density electromyography (HDEMG) wearable interfaces that enable people with severe loss of motor and hand function (due to spinal cord injury or neurodegenerative diseases) to embody physically assistive mobile manipulators in their home. Towards broader adoption of EMG as an interface to robots, I’ll also share a new benchmarking suite for learning-based generalization of EMG signals. I will then present our recent work in robot learning, including online and offline policy learning, to perform complex manipulation in assistive scenarios. This includes learning reward functions and robot control policies entirely from real-world videos of assistance, a framework for integrating LLMs into physically assistive robots, and new opportunities presented by generative simulation.

Biography

Zackory Erickson is an Assistant Professor in The Robotics Institute at Carnegie Mellon University, where he leads the Robotic Caregiving and Human Interaction (RCHI) Lab. His research focuses on developing new robot learning, mobile manipulation, and multimodal sensing methods for physical human-robot interaction and healthcare. Zackory received his PhD in Robotics from Georgia Tech. He and his students have received the Best Paper Award at HRI 2024, Best Student Paper Award at ICORR 2019, and a Best Paper in Service Robotics finalist at ICRA 2019.