PlanIt: A Crowdsourcing Approach for Learning to Plan Paths from Large Scale Preference Feedback
This work addresses the challenge of personalizing robot path planning for non-expert users in human-rich settings, representing an incremental improvement through crowdsourced data collection.
The paper tackles the problem of learning user preferences for robot trajectories in complex environments by developing a crowdsourcing system called PlanIt to collect large-scale feedback, and demonstrates that the learned cost function generates preferred trajectories across 122 navigation and manipulation tasks.
We consider the problem of learning user preferences over robot trajectories for environments rich in objects and humans. This is challenging because the criterion defining a good trajectory varies with users, tasks and interactions in the environment. We represent trajectory preferences using a cost function that the robot learns and uses it to generate good trajectories in new environments. We design a crowdsourcing system - PlanIt, where non-expert users label segments of the robot's trajectory. PlanIt allows us to collect a large amount of user feedback, and using the weak and noisy labels from PlanIt we learn the parameters of our model. We test our approach on 122 different environments for robotic navigation and manipulation tasks. Our extensive experiments show that the learned cost function generates preferred trajectories in human environments. Our crowdsourcing system is publicly available for the visualization of the learned costs and for providing preference feedback: \url{http://planit.cs.cornell.edu}