Multi-environment POMDPs (ME-POMDPs) extend standard POMDPs with discrete model uncertainty. ME-POMDPs represent a finite set of POMDPs that share the same state, action, and observation spaces, but may arbitrarily vary in their transition, observation, and reward models. Such models arise, for instance, when multiple domain experts disagree on how to model a problem. The goal is to find a single policy that is robust against any choice of POMDP within the set, *i.e.*, a policy that maximizes the worst-case reward across all POMDPs. We generalize and expand on existing work in the following way. First, we show that ME-POMDPs can be generalized to POMDPs *with sets of initial beliefs*, which we call *adversarial-belief POMDPs* (AB-POMDPs). Second, we show that any arbitrary ME-POMDP can be reduced to a ME-POMDP that only varies in its transition and reward functions or only in its observation and reward functions, while preserving (optimal) policies. We then devise exact and approximate (point-based) algorithms to compute robust policies for AB-POMDPs, and thus ME-POMDPs. We demonstrate that we can compute policies for standard POMDP benchmarks extended to the multi-environment setting.

Small, lighter-than-air (LTA) robotic airship platforms offer an alternative to the more common, rotor-based Unmanned Aerial Vehicles (UAVs). LTA vehicles are attractive due to their inherent safety, mobility, low power consumption, and extended flight times, making them suitable for operation in populated indoor environments. This paper explores the use of shared control strategies for teleoperation of miniature indoor robotic airships, paired with an autonomous landing and charging system. The teleoperation scheme passes the operator inputs to the airship actuators in a standardized manner, allowing for simple integration with various control input devices. Specifically, this work employs three different devices with distinctive user input mechanics. The autonomous landing system relies on ArUco markers and an on-board camera for state estimation. The developed docking station relies on a magnet-based winch mechanism that catches and pulls the airship to the appropriate position for charging. Finally, the shared control teleoperation framework is validated through a series of experiments involving user-guided indoor exploration and autonomous landing, with promising results.