Many robot tasks impose constraints on the workspace. For example, a robot may need to move a container without spilling its contents or open a door following the doorknob’s arc. Such constraints may induce narrow volumes in the configuration space, traditionally a challenge for sampling-based methods, and further cause infeasibility. We extend sample-driven connectivity learning (SDCL), a robust approach for planning with narrow passages, to develop a sampling ensemble for workspace constraints. In particular, the ensemble combines SDCL, projection via dual quaternion optimization, and random sampling. These complementary sampling approaches support efficient and robust planning under workspace constraints. Further, this framework offers the ability to determine infeasibility under workspace constraints, which is unaddressed by previous constrained planning methods.

Using robots to collect data is an effective way to obtain information from the environment and communicate it to a static base station. Furthermore, robots have the capability to communicate with one another, potentially decreasing the time for data to reach the base station. We present a Mixed Integer Linear Program that reasons about discrete routing choices, continuous robot paths, and their effect on the latency of the data collection task. We analyze our formulation, discuss optimization challenges inherent to the data collection problem, and propose a factored formulation that finds optimal answers more efficiently. Our work is able to find paths that reduce latency by up to 101% compared to treating all robots independently in our tested scenarios.

Exploring robots may fail due to environmental hazards. Thus, robots need to account for the possibility of failure to plan the best exploration paths. Optimizing expected utility enables robots to find plans that balance achievable reward with the inherent risks of exploration. Moreover, when robots rendezvous and communicate to exchange observations, they increase the probability that at least one robot is able to return with the map. Optimal exploration is NP-hard, so we apply a constraint-based approach to enable highly-engineered solution techniques. We model exploration under the possibility of robot failure and communication constraints as an integer, linear program and a generalization of the Vehicle Routing Problem. Empirically, we show that for several scenarios, this formulation produces paths within 50% of a theoretical optimum and achieves twice as much reward as a baseline greedy approach.