The success of autonomous vehicles has made path planning in real, physically grounded environments an increasingly important problem. In environments where speed matters and vehicles must maneuver around obstructions, such as autonomous car navigation in hostile environments, the speed with which real vehicles can traverse a path is often dependent on the sharpness of the corners on the path as well as the length of path edges. We present an algorithm that incorporates the use of the turn angle through path nodes as a limiting factor for vehicle speed. Vehicle speed is then used in a time-weighting calculation for each edge. This allows the path planning algorithm to choose potentially longer paths, with less turns in order to minimize path traversal time. Results simulated in the Breve environment show that travel time can be reduced over the solution obtained using the Anytime D* Algorithm by approximately 10% for a vehicle that is speed limited based on turn rate.

A metareasoning problem involves three parts: 1) a set of concrete problem domains; 2) reasoners to reason about the problems; and, 3) metareasoners to reason about the reasoners. We believe that the metareasoning community would benefit from agreeing on the first two problems. To support this kind of collaboration, we offer an open source 3D simulator containing everyday, commonsense problems that take place in kitchens. This paper presents several arguments for using a simulator to solve commonsense problems. The paper concludes by describing future work in simulator-based unified generative benchmarks for AI.

Representations that combine first-order logic and probability have been the focus of much recent research. Lifted inference algorithms for them avoid grounding out the domain, bringing benefits analogous to those of resolution theorem proving in first-order logic. However, all lifted probabilistic inference algorithms to date treat potentials as black boxes, and do not take advantage of their logical structure. As a result, inference with them is needlessly inefficient compared to the logical case. We overcome this by proposing the first lifted probabilistic inference algorithm that exploits determinism and context specific independence. In particular, we show that AND/OR search can be lifted by introducing POWER nodes in addition to the standard AND and OR nodes. Experimental tests show the benefits of our approach.

Approximation (WARA-2010), scheduled to be held on July Topics of interest for this AAAI workshop include all 12, 2010 in Atlanta, Georgia, USA in conjunction with aspects of abstraction, reformulation and approximation, AAAI-10, aims to provide a forum for intensive interaction including (but not limited to) the following: new techniques among researchers in all areas of artificial intelligence for automatically constructing and selecting appropriate and computer science with an interest in the different aspects ARA methods; frameworks that unify and classify of abstraction, reformulation, and approximation techniques. ARA techniques; empirical and theoretical studies of the The goal and scope of this workshop are similar to costs and benefits of ARA; applications of ARA to search, an independent symposium called SARA. The diverse backgrounds constraint satisfaction, deterministic and probabilistic planning, of participants of previous SARA symposia has led theorem proving, logic programming, game playing, to a rich and lively exchange of ideas, allowed the comparison parallel and distributed search, distributed data and knowledge of goals, techniques, and paradigms, and helped identify bases, internet search and navigation, knowledge compilation, important research issues and engineering hurdles. This knowledge acquisition, knowledge reformulation, workshop continues to do the same.

Markov logic networks (MLNs) use first-order formulas to define features of Markov networks. Current MLN structure learners can only learn short clauses (4-5 literals) due to extreme computational costs, and thus are unable to represent complex regularities in data. To address this problem, we present LSM, the first MLN structure learner capable of efficiently and accurately learning long clauses. LSM is based on the observation that relational data typically contains patterns that are variations of the same structural motifs. By constraining the search for clauses to occur within motifs, LSM can greatly speed up the search and thereby reduce the cost of finding long clauses. LSM uses random walks to identify densely connected objects in data, and groups them and their associated relations into a motif. Our experiments on three real-world datasets show that our approach is 2-5 orders of magnitude faster than the state-of-the-art ones, while achieving the same or better predictive performance.

We consider the problem of discrete multi-label entity classification in images. We argue that the framework of Markov Logic can provide a unified, well-grounded mechanism to incorporate arbitrary logical relationships between entities to improve classification in images, and thus generalizes much of the recent work on exploiting local and global context in object recognition and scene understanding. Furthermore, we show that Markov Logic can provide a powerful new set of contexts that can relate entities across images in a database for joint classification of all entities in a test set simultaneously. We relate this collective classification of images to graph-based semi-supervised learning approaches, and show that Markov Logic can effectively provide a method to unify context-related work with semi-supervised approaches in a way that neither techniques could easily do on their own. Finally, we show the efficacy of these techniques on a face recognition task on three datasets showing that adding contextual relations dramatically improves accuracy over semi-supervised learning approaches alone.

Many approaches were explored in recent years to introduce principles of metacognition and meta-learning into cognitive architectures, yet none of them resulted in a scalable human-like learner. This work presents an approach intended to fill the gap between human self-regulated learners and artificial learners by introducing a new spin of the familiar core cognitive architecture paradigm, taking it to a meta-level. The resultant architecture enables in artifacts exclusively human higher cognitive and learning abilities: specifically, deliberative new knowledge construction. Model predictions agree with results of a pilot study with human subjects.

Many task execution techniques tend to repeatedly invoke motion planning algorithms in order to perform complex tasks. In order to accelerate the perform of such methods, we present a real-time global motion planner that utilizes the computational capabilities of current many-core GPUs (graphics processing units). Our approach is based on randomized sample-based planners and we describe highly parallel algorithms to generate samples, perform collision queries, nearest-neighbor computations, local planning and graph search to compute collision-free paths for rigid robots. Our approach can efficiently solve the single-query and multiquery versions of the planning problem and can obtain one to two orders of speedup over prior CPU-based global planning algorithms. The resulting GPU-based planning algorithm can also be used for real-time feedback for task execution in challenging scenarios.

Learning, which aims at combining probabilistic graphical Markov networks have proved to be a very useful tool to models with first order logics representations. The represent probability distributions over large domains (see work that we present in this paper has been motivated by for instance, Chapter 8 in (Bishop 2006)). A Markov Network Markov Logic Networks (MLN), introduced in (Richardson is an undirected graphical model, where variables are and Domingos 2006). A Markov Logic Network is defined represented by nodes and features on subsets of variables by a set of weighted first-order formulas.

Dynamic executio n is a flexible plan execution technique in which a plan executive schedules and executes tasks dynamically at runtime in response to disturbances in order to satisfy plan constraints. In this paper, we extend dynamic execution to temporally and spatially flexible plans which, 1) execute tasks conditionally based on runtime state, and 2) support error recovery for anticipated runtime constraint violations. To accomplish these goals, we broaden our focus from dynamic execution of flexible plans to dynamic execution of flexible reactive programs. First, we introduce the Reactive Model-based Programming Language (RMPL) which, in addition to modeling temporal and spatial flexibility, includes three reactive programming language constructs: conditional execution, iteration, and exception handling. Then, we develop a probabilistic particle-sampling based dynamic execution algorithm which reasons efficiently over future program states to schedule tasks dynamically at runtime in order to satisfy program constraints. In addition, the algorithm monitors its own progress and notifies the executive if at any time the likelihood of successful program execution drops below a specified probability bound, δ.