Showing papers by "Maxim Likhachev published in 2005"

Fast replanning for navigation in unknown terrain

Abstract: Mobile robots often operate in domains that are only incompletely known, for example, when they have to move from given start coordinates to given goal coordinates in unknown terrain. In this case, they need to be able to replan quickly as their knowledge of the terrain changes. Stentz' Focussed Dynamic A/sup */ (D/sup */) is a heuristic search method that repeatedly determines a shortest path from the current robot coordinates to the goal coordinates while the robot moves along the path. It is able to replan faster than planning from scratch since it modifies its previous search results locally. Consequently, it has been extensively used in mobile robotics. In this article, we introduce an alternative to D/sup */ that determines the same paths and thus moves the robot in the same way but is algorithmically different. D/sup */ Lite is simple, can be rigorously analyzed, extendible in multiple ways, and is at least as efficient as D/sup */. We believe that our results will make D/sup */-like replanning methods even more popular and enable robotics researchers to adapt them to additional applications.

Anytime dynamic A*: an anytime, replanning algorithm

Abstract: We present a graph-based planning and replanning algorithm able to produce bounded suboptimal solutions in an anytime fashion. Our algorithm tunes the quality of its solution based on available search time, at every step reusing previous search efforts. When updated information regarding the underlying graph is received, the algorithm incrementally repairs its previous solution. The result is an approach that combines the benefits of anytime and incremental planners to provide efficient solutions to complex, dynamic search problems. We present theoretical analysis of the algorithm, experimental results on a simulated robot kinematic arm, and two current applications in dynamic path planning for outdoor mobile robots.

A Guide to Heuristic-based Path Planning

Abstract: We describe a family of recently developed heuristicbased algorithms used for path planning in the real world. We discuss the fundamental similarities between static algorithms (e.g. A*), replanning algorithms (e.g. D*), anytime algorithms (e.g. ARA*), and anytime replanning algorithms (e.g. AD*). We introduce the motivation behind each class of algorithms, discuss their use on real robotic systems, and highlight their practical benefits and disadvantages.

Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees

Abstract: MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start state to a goal, restricting computation to states relevant to this task can make much larger problems tractable. We introduce a new algorithm, Bounded RTDP, which can produce partial policies with strong performance guarantees while only touching a fraction of the state space, even on problems where other algorithms would have to visit the full state space. To do so, Bounded RTDP maintains both upper and lower bounds on the optimal value function. The performance of Bounded RTDP is greatly aided by the introduction of a new technique to efficiently find suitable upper bounds; this technique can also be used to provide informed initialization to a wide range of other planning algorithms.

Adaptive A

Abstract: Agents often have to perform repeated on-line searches as they gain additional knowledge about their environment. We describe an incremental version of A*, called Adaptive A*, that solves series of similar search problems faster than running A* repeatedly from scratch because it updates its heuristics between search episodes. It is simpler than other incremental versions of A* and thus likely easier to extend and adapt to new applications.

A generalized framework for Lifelong Planning A* search

Abstract: Recently, it has been suggested that Lifelong Planning A* (LPA*), an incremental version of A*, might be a good heuristic search-based replanning method for HSP-type planners. LPA* uses consistent heuristics and breaks ties among states with the same f-values in favor of states with smaller g-values. However, HSP-type planners use inconsistent heuristics to trade off plan-execution cost and planning time. In this paper, we therefore develop a general framework that allows one to develop more capable versions of LPA* and its nondeter-ministic version Minimax LPA*, including versions of LPA* and Minimax LPA* that use inconsistent heuristics and break ties among states with the same f-values in favor of states with larger g-values. We then show experimentally that the new versions of LPA* indeed speed it up on grids and thus promise to provide a good foundation for building heuristic search-based replanners.

Search-based planning for large dynamic environments

Abstract: Agents operating in the real world often have to act under the conditions where time is critical: there is a limit on the time they can afford to spend on deliberating what action to execute next. Planners used by such agents must produce the best plans they can find within the amount of time available. The strategy of always searching for an optimal plan becomes infeasible in these scenarios. Instead, we must use an anytime planner. Anytime planners operate by quickly finding a highly suboptimal plan first, and then improving it until the available time runs out. In addition to the constraints on time, world models used by planners are usually imperfect and environments are often dynamic. The execution of a plan therefore often results in unexpected outcomes. An agent then needs to update the model accordingly and re-execute a planner on the new model. A planner that has a replanning capability (a.k.a. an incremental planner) can substantially speed up each planning episode in such cases, as it tries to make use of the results of previous planning efforts in finding a new plan. Combining anytime with replanning capabilities is thus beneficial. For one, at each planning episode it allows the planner to produce a better plan within the available time: both in finding the first plan as well as in improving it, the planner can use its replanning capability to accelerate the process. In addition, the combination allows one to interleave planning and execution effectively. While the agent executes the current plan, the planner can continue improving it without having to discard all of its efforts every time the model of the world is updated. This thesis concentrates on graph-based searches. It presents an alternative view of A* search, a widely popular heuristic search in AI, and then uses this view to easily derive three versions of A* search: an anytime version, an incremental version and a version that is both anytime and incremental. Each of these algorithms is also able to provide a non-trivial bound on the suboptimality of the solution it generates. We believe that the simplicity, the existence of suboptimality bounds and the generality of the presented methods contribute to the research and development of planners well suited for systems operating in the real world.

Spatio-Temporal Case-Based Reasoning for Efficient Reactive Robot Navigation

Abstract: : This paper presents an approach to automatic selection and modification of behavioral assemblage parameters for autonomous navigation tasks. The goal of this research is to make obsolete the task of manual configuration of behavioral parameters, which often requires significant knowledge of robot behavior and extensive experimentation, and to increase the efficiency of robot navigation by automatically choosing and fine-tuning the parameters that fit the robot task-environment well in real time. The method is based on the Case-Based Reasoning paradigm. Derived from incoming sensor data, this approach computes spatial features of the environment. Based on the robot's performance, temporal features of the environment are then computed. Both sets of features are then used to select and fine-tune a set of parameters for an active behavioral assemblage. By continuously monitoring the sensor data and performance of the robot, the method re-selects these parameters as necessary. While a mapping from environmental features onto behavioral parameters (i.e., the cases) can be hard-coded, a method for learning new and optimizing existing cases also is presented. This completely automates the process of behavioral parameterization. The system was integrated within a hybrid robot architecture and extensively evaluated using simulations and indoor and outdoor real-world robotic experiments in multiple environments and sensor modalities, clearly demonstrating the benefits of the approach.