: The performance of single-camera SLAM is improved when wide-angle optics provide a field of view greater than the 40 to 50 degrees lenses normally used in computer vision. The is...
Autonomous planetary rovers operating in vast unknown environments must operate efficiently because of size, power and computing limitations. Recently, we have developed a rover c...
Sanjiv Singh, Reid G. Simmons, Trey Smith, Anthony...
An agent must acquire internal representation appropriate for its task, environment, sensors. As a learning algorithm, reinforcement learning is often utilized to acquire the rela...
—Three dimensional vision applications, such as robot vision, require modeling of the relationship between the two-dimensional images and the three-dimensional world. Camera cali...
As robots become a mass consumer product, they will need to learn new skills by interacting with typical human users. Past approaches have adapted reinforcement learning (RL) to a...