Using SyGuS to Synthesize Reactive Motion Plans
This addresses robot motion planning in dynamic environments, but it is incremental as it applies an existing formalism (SyGuS) to a new domain.
The paper tackles the problem of synthesizing reactive robot motion plans by reducing it to Syntax-Guided Synthesis (SyGuS) specifications, resulting in a method that generates a single program for reaching targets from any state and handles adversarial obstacles.
We present an approach for synthesizing reactive robot motion plans, based on compilation to Syntax-Guided Synthesis (SyGuS) specifications. Our method reduces the motion planning problem to the problem of synthesizing a function that can choose the next robot action in response to the current state of the system. This technique offers reactivity not by generating new motion plans throughout deployment, but by synthesizing a single program that causes the robot to reach its target from any system state that is consistent with the system model. This approach allows our tool to handle environments with adversarial obstacles. This work represents the first use of the SyGuS formalism to solve robot motion planning problems. We investigate whether using SyGuS for a bounded two-player reachability game is practical at this point in time.