In many applications a user attempts to configure a complex object with many possible internal choices. Recommendation engines that automatically configure such objects given user preferences and constraints, may provide much value in such cases. These applications offer the user various methods to provide the input and generate appropriate recommendations. It is likely, though, that the user will not be able to fully express her preferences and constraints, requiring a phase of manual tuning of the recommended configuration. We suggest that following this manual revision, additional constraints and preferences can be automatically collected, and the recommended configuration can be automatically improved. Specifically, we suggest a recommender component that takes as input an initial manual configuration of a complex object, deduces certain user preferences and constraints from this configuration, and constructs an alternative configuration. We show an appealing application for our method in complex trip planning, and demonstrate its usability in a user study.

The recommendation of additional shopping items that are potentially interesting for the customer has become a standard feature of modern online stores. In academia, research on recommender systems (RS) is mostly centered around approaches that rely on explicit item ratings and long-term user profiles. In practical environments, however, such rating information is often very sparse and for a large fraction of the users very little is known about their preferences. Furthermore, in particular when the shop offers products from a variety of categories, the decision of what should be recommended can strongly depend on the user's current short-term interests and the navigational context. In this paper, we report the results of an initial experimental analysis evaluating the predictive accuracy of different contextualized and non-contextualized recommendation strategies and discuss the question of appropriate experimental designs for such types of evaluations. To that purpose, we introduce a parameterizable protocol that supports session-specific accuracy measurements. Our analysis, which was based on log data obtained from a large online retailer for clothing and lifestyle products, shows that even a comparably simple contextual post-processing approach based on product features can leverage short-term user interests to increase the accuracy of the recommendations.

We consider the problem of personalized text-based music retrieval where users' history of preferences are taken into account in addition to their issued textual queries.Current retrieval methods mostly rely on songs meta-data. This limits the query vocabulary. Moreover, it is very costly to gather this information in large collections of music. Alternatively, we use music annotations retrieved from social tagging Websites such as last.fm and use them as textual descriptions of songs. Considering a user's profile and using preference patterns of music among all users, as in collaborative filtering approaches, can be useful in providing personalized and more satisfactory results. The main challenge is how to include both users' profiles and the songs meta-data in the retrieval model. In this paper, we propose a hierarchical probabilistic model that takes into account the users' preference history as well as tag co-occurrences in songs. Our model is an extension of LDA where topics are formed as joint clusterings of songs and tags. These topics capture the tag associations and user preferences and correspond to different music tastes. Each user's profile is represented as a distribution over topics which shows the user's interests in different types of music.We will explain how our model can be used for contextual retrieval. Our experimental results show significant improvement in retrieval when user profiles are taken into account.

Traditional recommender systems try to provide users with recommendations which maximize the probability that the user will accept them. Recent studies have shown that recommender systems have a positive effect on the provider’s revenue. In this paper we show that by giving a different set of recommendations, the recommendation system can further increase the business’ utility (e.g. revenue), without any significant drop in user satisfaction. Indeed, the recommendation system designer should have in mind both the user, whose taste we need to reveal, and the business, which wants to promote specific content. In order to study these questions, we performed a large body of experiments on Amazon Mechanical Turk. In each of the experiments, we compare a commercial state-of-the-art recommendation engine with a modified recommendation list, which takes into account the utility (or revenue) which the business obtains from each suggestion that is accepted by the user. We show that the modified recommendation list is more desirable for the business, as the end result gives the business a higher utility (or revenue). To study possible longterm effects of giving the user worse suggestions, we asked the users how they perceive the list of recommendation that they received. Our findings are that any difference in user satisfaction between the list is negligible, and not statistically significant. We also uncover a phenomenon where movie consumers prefer watching and even paying for movies that they have already seen in the past than movies that are new to them.

List of organizers of the Intelligent Robotic Systems AAAI 2013 workshop.

This paper addresses the problem of overcoming visual perception limitations in service robots with remote assistance from human users. In particular, consider a scenario where a user requests the robot to perform some task that requires a perceptual ability, e.g., check if a specific mug, "my mug," is in the lab or in an office, but the robot may not know how to recognize that object. We propose to equip the robots with the abilities to: (i) identify their own perceptual limitations, (ii) autonomously and remotely query human users for assistance, and (iii) learn new object descriptors from the interaction with humans. We successfully developed a complete initial version of our approach on our CoBot service mobile robot. The interaction with the user builds upon our previously developed semi-autonomous telepresence image sharing and control. The user can now further identify the object and the robot can save the descriptor and use it in future situations. We illustrate our work with the task of learning to identify an object in the environment, and to report its presence to a user. Our ongoing work includes addressing a dynamic interaction between the robot and the remote user for visual focus of attention and different object viewing, as well as the effective storage, labeling, accessing, and sharing of multiple learned object descriptors, in particular among robots. Our goal is also to contribute the learned knowledge to crowd-robotics efforts.

This paper presents a novel method for qualitative mapping of large scale spaces. The proposed framework makes use of a graphical representation of the world in order to build a map consisting of qualitative constraints on the geometric relationships between landmark triplets. A novel measurement method based on camera imagery is presented which extends previous work from the field of Qualitative Spatial Reasoning. Measurements are fused into the map using a deterministic approach based on iterative graph updates and permutation operators. Experimental results are presented for a robot traversing a Mars-like environment while building a relational map.

This paper discusses the problem of generating efficient coverage paths for a mobile robot in an adversarial environment, where threats exist that might stop the robot. First, we formally define the problem of adversarial coverage, and present optimization criteria used for evaluation of coverage algorithms in adversarial environments. We then present a coverage area planning algorithm based on a map of the probable threats. The algorithm tries to minimize the total risk involved in covering the target area while taking into account coverage time constrains. The algorithm is based on incrementally extending the coverage path to the nearest safe cells while allowing the robot to repeat its steps. By allowing the robot to visit each cell in the target area more than once, the accumulated risk can be reduced at the expense of extending the coverage time. We show the effectiveness of this algorithm in extensive experiments.

The need for high-level task planning in robotics is well understood. However, interfacing discrete planning with continuous actions often requires extensive engineering of the solution. For instance, picking up an object may require removing many others that obstruct it. Identifying the exact obstructions requires geometric reasoning which is prohibitively expensive to precompute, with results that are difficult to represent efficiently at the level of a discrete planner. We propose a new approach that utilizes representation techniques from first-order logic and provides a method for synchronizing between continuous and discrete planning layers. We evaluate the approach and illustrate its robustness through a number of experiments using a state-of-the-art robotics simulator, accomplishing a variety of challenging tasks like picking objects from cluttered environments, where the planner needs to figure out which other objects need to be moved first to be able to reach the target object, and laying out a table for dinner, where the planner figures out effective tray-loading, navigation and unloading strategies.

Although planning for the tasks a household robot has to perform appears to be easy, there exists the problem that the robot is usually uncertain about the state of the household when starting to plan. For example, when getting the order of tidying up the kitchen, the robot does not know what objects it will have to put away and whether there are actually any objects that need to be put away. Furthermore, while sensing operations can provide moreinformation about the environment, things can go wrong when executingan action. In this paper, we try to identify conditions under which classical planning can be used in a replanning loop in order to solve the planning problem in nondeterministic partially observable open domains. In particular, we will define completeness and soundness of replanning with respect to nondeterministic planning and we will identify a PSPACE-checkable condition that guarantees soundness.