Dynamic programming with incomplete information to overcome navigational uncertainty in a nautical environment
This work addresses navigation safety and cost-efficiency for autonomous maritime systems, but it is incremental as it builds on existing dynamic programming and POMDP methods in a toy environment.
The paper tackled the problem of navigational uncertainty in a nautical environment by applying dynamic programming to a partially observed Markov decision process (POMDP) with incomplete information, resulting in navigation policies that outperformed traditional MDP-based dynamic programming in safety and reduced measurement costs with controlled sensing.
Using a novel toy nautical navigation environment, we show that dynamic programming can be used when only incomplete information about a partially observed Markov decision process (POMDP) is known. By incorporating uncertainty into our model, we show that navigation policies can be constructed that maintain safety, outperforming the baseline performance of traditional dynamic programming for Markov decision processes (MDPs). Adding in controlled sensing methods, we show that these policies can also lower measurement costs at the same time.