Towards Autonomous Robots for Healthcare

Advances in robotics have the potential to improve healthcare, from enabling surgical procedures that are beyond current clinical capabilities to assisting people with daily tasks in their homes. In this talk, we will discuss new algorithms to enable medical and assistive robots to operate autonomously by learning and planning their motions. We begin by showing the feasibility and advantages of deploying autonomous medical robots in living tissue with the goal of achieving unprecedented levels of accuracy and precision, reducing the physicians’ mental load so they can focus on other aspects of the procedure, and improving patient outcomes. We present the first medical robot capable of autonomously maneuvering a needle to reach a target while avoiding anatomical obstacles in living tissue. Motivated by lung cancer, which kills over 120,000 Americans each year, the medical robot used a steerable needle to access sites within living, breathing lungs for diagnosis and treatment. The robot’s steerable needle automatically maneuvered around anatomical obstacles to perform procedures at sites not safely reachable using traditional instruments. We also demonstrated that our approach offers greater accuracy compared with a standard human-controlled technique. Next, I will present novel algorithms for robotic assistance in the home using demonstration-guided motion planning, an approach in which the robot first learns an assistive task from human-conducted demonstrations and then autonomously plans motions to accomplish the learned task in new, dynamic environments cluttered with obstacles. Our results show the benefits and potential of deploying autonomous robots to improve healthcare, both in hospitals and in homes.