Analyzing Human Models that Adapt Online
This addresses safety concerns for robots in domains like autonomous driving and indoor navigation, but it is incremental as it applies existing analysis tools to a new context.
The paper tackles the problem of analyzing safety-related questions for robots using predictive human models that adapt online, such as how quickly a robot can confidently estimate a human's goal, by modeling the learning algorithm as a dynamical system and using reachability analysis and optimal control to compute learnable hypotheses and learning times.
Predictive human models often need to adapt their parameters online from human data. This raises previously ignored safety-related questions for robots relying on these models such as what the model could learn online and how quickly could it learn it. For instance, when will the robot have a confident estimate in a nearby human's goal? Or, what parameter initializations guarantee that the robot can learn the human's preferences in a finite number of observations? To answer such analysis questions, our key idea is to model the robot's learning algorithm as a dynamical system where the state is the current model parameter estimate and the control is the human data the robot observes. This enables us to leverage tools from reachability analysis and optimal control to compute the set of hypotheses the robot could learn in finite time, as well as the worst and best-case time it takes to learn them. We demonstrate the utility of our analysis tool in four human-robot domains, including autonomous driving and indoor navigation.