Spelling suggestions: "subject:"human guided achine 1earning"" "subject:"human guided achine _learning""
1 |
Towards Improving and Extending Traditional Robot Autonomy with Human Guided Machine LearningCesar-Tondreau, Brian 05 October 2022 (has links)
Traditional autonomy among robotic and other artificial agents was accomplished via automated planning methods that found a viable sequence of actions, which, if executed by an agent, would result in the successful completion of the given task(s). However, many tasks that we would like robotic agents to perform involve goals that are complex, poorly-defined, or hard to specify. Furthermore, significant amounts of data or computation are required for agents to reach reasonable performance. As a result, autonomous systems still rely on human operators to play a supervisory role to ensure that robotic operations are completed quickly and successfully. The presented work aims to improve the traditional methods of robot autonomy by developing an intuitive means for(human operators to adapt/mold the behaviors and decision making of autonomous agents) autonomous agents to leverage the flexibility and expertise of human end users. Specifically, this work shows the results of three machine learning-based approaches for modifying and extending established robot navigation behaviors and skills through human demonstration. Our first project combines Imitation learning with classical navigation software to achieve long-horizon planning and navigation that follows navigation rules specified by a human user. We show that this method can adapt a robot's navigation behavior to become more like that of a human demonstrator. Moreover, for a minimal amount of demonstration data, we find that this approach outperforms recent baselines in both navigation success rate and trajectory similarity to the demonstrator. In the second project, we introduce a method of communicating complex skills over a short-horizon task. Specifically, we explore using imitation learning to teach a robot the complex skill needed to safely navigate through negative obstacles in simulation. We find that this proposed method could imitate complex navigation behaviors and generalize to novel environments in simulation with minimal demonstration. Furthermore, we find that this method compares favorably to a classical motion planning algorithm which was modified to assign traversal cost based on the terrain slope local to the robot's current pose. Finally, we demonstrate a practical implementation of the second approach in a real-world environment. We show that the proposed method results in a policy that can generalize across differently shaped obstacles and across simulation and reality. Moreover, we show that the proposed method still outperforms the classical motion planning algorithm when tasked to navigate negative obstacles in the real world. / Doctor of Philosophy / With the rapid advancement of computing power and growing technical literacy of the general public, the tasks that robots should be able to accomplish have multiplied. Robots can, however, be limited by the human ability to effectively convey how tasks should be performed. For example, autonomous robot navigation to a specified path planning software suite that generates feasible and obstacle-free trajectories through a cluttered environment. While these modules can be modified to meet task-specific constraints and user preferences, current modification procedures require substantial effort on the part of an expert roboticist with a great deal of technical training. The desired tasks and skills are difficult to effectively convey in a machine legible format. These tasks often require technical expertise in multiple mechatronic disciplines and hours of hand tuning that the typical end user does not have. In this dissertation, we examine methods that directly leverage human users to teach robots how to perform tasks that are generally difficult to specify pragmatically. We focus on methods that allow human users to extend established robot navigation behaviors and skills by demonstrating their own preferred approaches. We evaluate the performances of our proposed approaches in terms of navigation success rate, adherence to the demonstrated behavior, and their ability to apply what they have learned to novel environments. Moreover, we showed that our approaches compare favorably to recent machine learning-based approaches to autonomous navigation, and classical navigation techniques with respect to these metrics.
|
Page generated in 0.0949 seconds