Robots operating in home environments must be able to interact with articulated objects such as doors or drawers.  Ideally, robots are able to autonomously infer articulation models by observation.  In this paper, we present an approach to learn kinematic models by inferring the connectivity of rigid parts and the articulation models for the corresponding links.  Our method uses a mixture of parameterized and parameter-free (Gaussian process) representations and finds low-dimensional manifolds that provide the best explanation of the given observations.  Our approach has been implemented and evaluated using real data obtained in various realistic home environment settings.

Road network information simplifies autonomous driving by providing strong priors about environments. It informs a robotic vehicle with where it can drive, models of what can be expected, and contextual cues that influence driving behaviors. Currently, however, road network information is manually generated using a combination of GPS survey and aerial imagery. These manual techniques are labor intensive and error prone. To full exploit the benefits of digital imagery, these processes should be automated. As a step toward this goal, we present an algorithm that extracts the structure of parking lot visible from a given aerial image. To minimize human intervention in the use of aerial imagery, we devise a self-supervised learning algorithm that automatically generates a set of parking spot templates to learn the appearance of a parking lot and estimates the structure of the parking lot from the learned model. The data set extracted from a single image alone is too small to sufficiently learn an accurate parking spot model. However, strong priors trained using large data sets collected across multiple images dramatically improvce performance. Our self-supervised approach outperforms the prior alone by adapting the distribution of examples toward that found in the current image. A thorough empirical analysis compares leading state-of-the-art learning techniques on this problem.

Exploration for robotic mapping is typically handled using greedy entropy reduction. Here we show how to apply information lookahead planning to a challenging instance of this problem in which an Autonomous Underwater Vehicle (AUV) maps hydrothermal vents. Given a simulation of vent behaviour we derive an observation function to turn the planning for mapping problem into a POMDP. We test a variety of information state MDP algorithms against greedy, systematic and reactive search strategies. We show that directly rewarding the AUV for visiting vents induces effective mapping strategies. We evaluate the algorithms in simulation and show that our information lookahead method outperforms the others.

We study path planning on grids with blocked and unblocked cells. Any-angle path-planning algorithms find short paths fast because they propagate information along grid edges without constraining the resulting paths to grid edges. Incremental path-planning algorithms solve a series of similar path-planning problems faster than repeated single-shot searches because they reuse information from the previous search to speed up the next one. In this paper, we combine these ideas by making the any-angle path-planning algorithm Basic Theta* incremental. This is non-trivial because Basic Theta* does not fit the standard assumption that the parent of a vertex in the search tree must also be its neighbor. We present Incremental Phi* and show experimentally that it can speed up Basic Theta* by about one order of magnitude for path planning with the freespace assumption.

We then describe In this paper, we describe a user evaluation of a humanrobot a study which assessed the responses of naïve users dialogue system that is designed to enable a humanoid to output that varied along two dimensions: the robot to cooperate with a human partner on building wooden method of describing an assembly plan (pre-order construction toys. In the evaluation, we experimentally vary or post-order), and the method of referring to objects two aspects of the output generated by the system: the way in the world (basic and full). Varying both that it describes assembly plans to the user, and the way that of these factors produced significant results: subjects it refers to objects in the world. We then measure the impact using the system that employed a pre-order of varying each of these features on the users' objective success description strategy asked for instructions to be repeated at working with the system, as well as on their subjective significantly less often than those who experienced impressions of the interaction.

We study the problem of multi-robot perimeter patrol in adversarial environments, under uncertainty of adversarial behavior. The robots patrol around a closed area using a nondeterministic patrol algorithm. The adversary's choice of penetration point depends on the knowledge it obtained on the patrolling algorithm and its weakness points. Previous work investigated full knowledge and zero knowledge adversaries, and the impact of their knowledge on the optimal algorithm for the robots. However, realistically the knowledge obtained by the adversary is neither zero nor full, and therefore it will have uncertainty in its choice of penetration points. This paper considers these cases, and offers several approaches to bounding the level of uncertainty of the adversary, and its influence on the optimal patrol algorithm. We provide theoretical results that justify these approaches, and empirical results that show the performance of the derived algorithms used by simulated robots working against humans playing the role of the adversary is several different settings.

To apply hierarchical task network (HTN) planning to real-world planning problems, one needs to encode the HTN schemata and action models beforehand. However, acquiring such domain knowledge is difficult and time-consuming because the HTN domain definition involves a significant knowledge-engineering effort. A system that can learn the HTN planning domain knowledge automatically would save time and allow HTN planning to be used in domains where such knowledge-engineering effort is not feasible. In this paper, we present a formal framework and algorithms to acquire HTN planning domain knowledge, by learning the preconditions and effects of actions and preconditions of methods. Our algorithm, HTN-learner, first builds constraints from given observed \emph{decomposition trees} to build action models and method preconditions. It then solves these constraints using a weighted MAX-SAT solver. The solution can be converted to action models and method preconditions. Unlike prior work on HTN learning, we do not depend on complete action models or state information. We test the algorithm on several domains, and show that our HTN-learner algorithm is both effective and efficient.

Our approach analyzes the data dependencies in the trace to discover the context of the actions that appear in the trace. Existing work on workflow mining ignores the Using the context information we can decide whether the two dataflow aspect of the problem. This is not acceptable occurrences of the same action correspond to the same node for service-oriented applications that use Web in the workflow or not. As a result, unlike the previous work services with typed inputs and outputs. We propose [van der Aalst et al., 2004; Cook and Wolf, 1998b; Agrawal a novel algorithm WIT (Workflow Inference from et al., 1998], we are able to learn workflows with non-unique Traces) which identifies the context similarities of action nodes. Furthermore, the context discovery can easily the observed actions based on the dataflow and uses be generalized to work with causal dependencies instead of model merging techniques to generalize the control data dependencies. Thus, the ideas presented in this work flow and the dataflow simultaneously. We identify can be applied to other areas such as learning domain specific the class of workflows that WIT can learn correctly.

In this paper we address the problem of generating preferred plans by combining the procedural control knowledge specified by Hierarchical Task Networks (HTNs) with rich user preferences. To this end, we extend the popular Planning Domain Definition Language, PDDL3, to support specification of simple and temporally extended preferences over HTN constructs. To compute preferred HTN plans, we propose a branch-and-bound algorithm, together with a set of heuristics that, leveraging HTN structure, measure progress towards satisfaction of preferences. Our preference-based planner, HTNPLAN-P, is implemented as an extension of the SHOP2 planner. We compared our planner with SGPLAN5 and HPLAN-P — the top performers in the 2006 International Planning Competition preference tracks. HTNPLAN-P generated plans that in all but a few cases equalled or exceeded the quality of plans returned by HPLAN-P and SGPLAN5. While our implementation builds on SHOP2, the language and techniques proposed here are relevant to a broad range of HTN planners.

Real-time dynamic programming (RTDP) solves Markov decision processes (MDPs) when the initial state is restricted, by focusing dynamic programming on the envelope of states reachable from an initial state set. RTDP often provides performance guarantees without visiting the entire state space.  Building on RTDP, recent work has sought to improve its efficiency through various optimizations, including maintaining upper and lower bounds to both govern trial termination and prioritize state exploration. In this work, we take a Bayesian perspective on these upper and lower bounds and use a value of perfect information (VPI) analysis to govern trial termination and exploration in a novel algorithm we call VPI-RTDP.  VPI-RTDP leads to an improvement over state-of-the-art RTDP methods, empirically yielding up to a three-fold reduction in the amount of time and number of visited states required to achieve comparable policy performance.