Learning Motion Predictors for Smart Wheelchair using Autoregressive Sparse Gaussian Process
This work addresses motion prediction for smart wheelchairs, enabling robotic control on unmodified commercial platforms, which is an incremental improvement for assistive technology users.
The authors tackled the problem of predicting motion for a smart wheelchair built on a commercial powered wheelchair platform, which avoids mechanical modifications but complicates robotic control due to black-box joystick transformations and odometer installation difficulties. They developed an integrated hardware and software system using an RGB-D camera and Arduino to capture data, with an autoregressive sparse Gaussian process model for prediction, and demonstrated its efficacy in real-world short-term path prediction experiments compared to a baseline neural network model.
Constructing a smart wheelchair on a commercially available powered wheelchair (PWC) platform avoids a host of seating, mechanical design and reliability issues but requires methods of predicting and controlling the motion of a device never intended for robotics. Analog joystick inputs are subject to black-box transformations which may produce intuitive and adaptable motion control for human operators, but complicate robotic control approaches; furthermore, installation of standard axle mounted odometers on a commercial PWC is difficult. In this work, we present an integrated hardware and software system for predicting the motion of a commercial PWC platform that does not require any physical or electronic modification of the chair beyond plugging into an industry standard auxiliary input port. This system uses an RGB-D camera and an Arduino interface board to capture motion data, including visual odometry and joystick signals, via ROS communication. Future motion is predicted using an autoregressive sparse Gaussian process model. We evaluate the proposed system on real-world short-term path prediction experiments. Experimental results demonstrate the system's efficacy when compared to a baseline neural network model.