We propose a novel planning technique for satisfying tasks specified in temporal logic in partially revealed environments. We define high-level actions derived from the environment and the given task itself, and estimate how each action contributes to progress towards completing the task. As the map is revealed, we estimate the cost and probability of success of each action from images and an encoding of that action using a trained neural network. These estimates guide search for the minimum-expected-cost plan within our model. Our learned model is structured to generalize across environments and task specifications without requiring retraining. We demonstrate an improvement in total cost in both simulated and real-world experiments compared to a heuristic-driven baseline.

Topological strategies for navigation meaningfully reduce the space of possible actions available to a robot, allowing use of heuristic priors or learning to enable computationally efficient, intelligent planning. The challenges in estimating structure with monocular SLAM in low texture or highly cluttered environments have precluded its use for topological planning in the past. We propose a robust sparse map representation that can be built with monocular vision and overcomes these shortcomings. Using a learned sensor, we estimate high-level structure of an environment from streaming images by detecting sparse "vertices" (e.g., boundaries of walls) and reasoning about the structure between them. We also estimate the known free space in our map, a necessary feature for planning through previously unknown environments. We show that our mapping technique can be used on real data and is sufficient for planning and exploration in simulated multi-agent search and learned subgoal planning applications.

The simulation of large systems of biochemical reactions is a key part of research into molecular signaling and information processing in biological cells. However, it can be impractical because many relevant reactions are modeled as stochastic, discrete event processes, and the complexity of the computing task scales with the number of discrete events in a simulation. Traditionally, such simulations are computed on general purpose CPUs, and sometimes in networks of such processors. We show that an alternative algorithm to the conventional approaches based on the Gillespie algorithm reveals a fine-grained parallel structure that is amenable to realization in FPGA hardware. A method is shown for compiling biochemical reaction systems into corresponding Verilog descriptions of simulators that employ this alternative algorithm. We describe a preliminary implementation of such a compiled accelerator that demonstrates the performance of this approach, achieving an initial performance that is 20 times faster than a competing general purpose CPU.