Robots can be made smarter if they can plan complex behaviors with real-time computations, rather than with predesigned or previously learned routines. Here is a great paper from Science that addresses this using Spectral Expansion Tree Search (SETS) and authored by Riviere, Lathrop and Chung. Authors abstract follows: “The ability of a robot to plan complex behaviors with real-time computation, rather than adhering to predesigned or offline-learned routines, alleviates the need for specialized algorithms or training for each problem instance. Monte Carlo tree search is a powerful planning algorithm that strategically explores simulated future possibilities, but it requires a discrete problem representation that is irreconcilable with the continuous dynamics of the physical world.…