Disney says its parks are "Where Dreams Come True," but that statement was never so literal as it was for two foster kids during a recent visit to the park. Janielle and Elijah Gilmour, ages 12 and 10, got the surprise of a lifetime in April, when foster parents Courtney and Tom Gilmour announced news of their official adoption date during a visit to Walt Disney World. "We planned it as soon as we got the [official] date, which was the Friday before our trip," Courtney tells Fox News. What Courtney didn't plan on, however, was that Disney would catch wind of the duo's plans and offer to lend a mouse-like, white-gloved hand. After arriving at the park from Portland, Penn., Courtney tweeted out a photo of the family's Walt Disney World celebration buttons, and the park got in touch to offer a private meet-and-greet with Mickey Mouse himself.

Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to construct a plan. Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans. Before any action, it can perform a variable number of imagination steps, which involve proposing an imagined action and evaluating it with its model-based imagination. All imagined actions and outcomes are aggregated, iteratively, into a "plan context" which conditions future real and imagined actions. The agent can even decide how to imagine: testing out alternative imagined actions, chaining sequences of actions together, or building a more complex "imagination tree" by navigating flexibly among the previously imagined states using a learned policy. And our agent can learn to plan economically, jointly optimizing for external rewards and computational costs associated with using its imagination. We show that our architecture can learn to solve a challenging continuous control problem, and also learn elaborate planning strategies in a discrete maze-solving task. Our work opens a new direction toward learning the components of a model-based planning system and how to use them.

We consider an orienteering problem (OP) where an agent needs to visit a series (possibly a subset) of depots, from which the maximal accumulated profits are desired within given limited time budget. Different from most existing works where the profits are assumed to be static, in this work we investigate a variant that has arbitrary time-dependent profits. Specifically, the profits to be collected change over time and they follow different (e.g., independent) time-varying functions. The problem is of inherent nonlinearity and difficult to solve by existing methods. To tackle the challenge, we present a simple and effective framework that incorporates time-variations into the fundamental planning process. Specifically, we propose a deterministic spatio-temporal representation where both spatial description and temporal logic are unified into one routing topology. By employing existing basic sorting and searching algorithms, the routing solutions can be computed in an extremely efficient way. The proposed method is easy to implement and extensive numerical results show that our approach is time efficient and generates near-optimal solutions.

The flight plan for the ill-fated 1970 Apollo 13 mission which had to be altered following the an emergency on board has been unearthed. The 352-page document bears the annotations made by all three crew members recording in detail the actions they had to take after an explosion ripped off part of their space ship. Apollo 13 was to be the third mission to land on the moon, but just under 56 hours into flight, an oxygen tank explosion forced the crew to cancel the lunar landing and move into the Aquarius lunar module to return back to Earth. The drama that unfolded during the Apollo 13 mission was re-told in the Hollywood film starring Tom Hanks, Kevin Bacon as Swigert and the late Bill Paxton as Haise. The mission is famous for the line ''Houston, we have had a problem here', which is often misquoted as'Houston, we have a problem'. The flight plan for the ill-fated Apollo 13 mission which had to be drastically altered following the'Houston, we have had a problem' emergency on board has been unearthed The Apollo 13 mission which set off on April 11, 1970 was meant to culminate in a third moon landing, with Lovell and Haise voyaging to the lunar surface while Swigert orbited in the command module Odyssey.

Being able to both walk and take flight is typical in nature, and now researchers are creating drones with similar capabilities. Scientists have developed a prototype drone that can both fly and drive - a breakthrough that could pave the way for flying cars in the future. The development could lead to machines that can fly into disaster zones and squeeze through tight spaces to transport objects or rescue people. The team developed various'path-planning' algorithms aimed at ensuring that the drones don't collide. To make them capable of driving, the team put two small motors with wheels on the bottom of each drone.

Although it's not a'one size fits all' solution, artificial intelligence can be used to successfully hunt cyberthreats. Giovanni Vigna, CTO and co-founder of Lastline, identifies several of the key areas to address when thinking proactively about AI as a tool in detecting cyberthreats. Artificial intelligence (AI) will not automatically detect and resolve every potential malware or cyberthreat incident, but when it combines both bad and good behavior modeling it becomes a successful and powerful weapon against even the most advanced malware. By their very nature, malware detection tools must constantly evolve to stay up to date with ever-changing crimeware. One of the biggest evolutions in malware detection is the migration from trapping to hunting.

Robots acting in human-scale environments must plan under uncertainty in large state-action spaces and face constantly changing reward functions as requirements and goals change. Planning under uncertainty in large state-action spaces requires hierarchical abstraction for efficient computation. We introduce a new hierarchical planning framework called Abstract Markov Decision Processes (AMDPs) that can plan in a fraction of the time needed for complex decision making in ordinary MDPs. AMDPs provide abstract states, actions, and transition dynamics in multiple layers above a base-level "flat" MDP . AMDPs decompose problems into a series of subtasks with both local reward and local transition functions used to create policies for subtasks. The resulting hierarchical planning method is independently optimal at each level of abstraction, and is recursively optimal when the local reward and transition functions are correct. We present empirical results showing significantly improved planning speed, while maintaining solution quality, in the Taxi domain and in a mobile-manipulation robotics problem. Furthermore, our approach allows specification of a decision-making model for a mobile-manipulation problem on a Turtlebot, spanning from low-level control actions operating on continuous variables all the way up through high-level object manipulation tasks.

In many robot motion planning problems such as manipulation planning for a personal robot in a kitchen or an industrial manipulator in a warehouse, all motion planning queries are in an environment that is largely static. Consequently, one should be able to improve the performance of a planning algorithm by training on this static environment ahead of operation time. In this work, we propose a method to improve the performance of heuristic search-based motion planners in such environments. The first, learning, phase of our proposed method analyzes search performance on multiple planning episodes to infer local minima zones, that is, regions where the existing heuristic(s) are weakly correlated with the true cost-to-go. Then, in the planning phase of the method, the learnt local minima are used to modify the original search graph in a way that improves search performance. We prove that our method preserves guarantees on completeness and bounded suboptimality with respect to the original search graph. Experimentally, we observe significant improvements in success rate and planning time for challenging 11 degree-of-freedom mobile manipulation problems.

Symbolic planning methods have proved to be challenging in robotics due to partial observability and noise as well as unavoidable exceptions to rules that symbol semantics depend on. Often the symbols that a robot considers to support for planning are brittle, making them unsuited for even relatively short term use. Maturing probabilistic methods in robotics, however, are providing a sound basis for symbol grounding that supports using probabilistic distributions over symbolic entities as the basis for planning. In this paper, we describe a belief-space planner that stabilizes the semantics of feedback from the environment by actively interacting with a scene. When distributions over higher-level abstractions stabilize, powerful symbolic planning techniques can provide reliable guidance for problem solving. We present such an approach in a hybrid planning scheme that actively controls uncertainty and yields robust state estimation with bounds on uncertainty that can make effective use of powerful symbolic planning techniques. We illustrate the idea in a hybrid planner for autonomous construction tasks with a real robot system.

Robot navigation through non-uniform environments requires reliable motion plan generation. The choice of planning model fidelity can significantly impact performance. Prior research has shown that reducing model fidelity saves planning time, but sacrifices execution reliability. While current adaptive hierarchical motion planning techniques are promising, we present a framework that leverages a richer set of robot motion models at plan-time. The framework chooses when to switch models and what model is most applicable within a single trajectory. For instance, more complex environment locales require higher fidelity models, while lower fidelity models are sufficient for simpler parts of the planning space, thus saving plan time. Our algorithm continuously aims to pick the model that best handles the current local environment. This effectively generates a single, mixed-fidelity plan. We present results for a simulated mobile robot with attached trailer in a hospital domain. We compare using a single motion planning model to switching with our framework of multiple models. Our results demonstrate that multi-fidelity model switching increases plan-time efficiency without sacrificing execution reliability.