Improving balance in robots is an ongoing field. In fact, robots are getting better at it all the time. Hybrid Robotics has shared a video that shows how Cassie, bipedal robot, can learn to ride hovershoes. The robot was tested riding hovershoes on rough and uneven outdoor train and up/down steep inclines.
As the researchers explain:
We created a framework for autonomous bipedal robotic locomotion using a wheeled platform. This framework includes a computer vision system, a path planner, and a feedback control strategy. In our experiments, we show the robustness of our controller through a variety of tasks, such as riding the Hovershoes down a few stairs, riding on rough and uneven outdoor terrain, riding up and down steep inclines, and leaning into a turn to quickly go around corners.
Cassie operates either by receiving translation and rotation velocity commands from an operator, or completely autonomously by detecting obstacles and planning paths around them to reach a goal location.