Scaling Observation-aware Planning in Uncertain Domains
For roboticists and AI engineers designing sensing systems, this work provides a scalable solution to a previously intractable problem, though it is domain-specific.
The authors tackle the Optimal Observability Problem (OOP) for POMDPs, developing a decomposition-based method that improves runtime by 5 orders of magnitude and scales to instances 3 orders of magnitude larger than prior work.
Deciding which sensing capabilities to deploy on an agent in uncertain domains is a fundamental engineering challenge, in which one balances task achievability against the high costs of hardware and processing. This problem has previously been formalized as the Optimal Observability Problem (OOP), based on the well-known Partially Observable Markov Decision Process (POMDP) model for decision-making. This work studies (sub-)symbolic techniques to scale solving of decidable fragments of the OOP, namely the Sensor Selection Problem (SSP) and the Positional Observability Problem (POP). Besides improving the original approach based on parameter synthesis, we develop a new solving method that identifies sensible observation functions via decomposition of POMDPs, improving performance by 3 and 5 orders of magnitude for instance size and runtime, respectively.