Nichola Abdo

Learning manipulation actions from a few demonstrations

To efficiently plan complex manipulation tasks, robots need to reason on a high level. Symbolic planning, however, requires knowledge about the preconditions and effects of the individual actions. In this work, we present a practical approach to learn manipulation skills, including preconditions and effects, based on teacher demonstrations. We believe that requiring only a small number of demonstrations is essential for robots operating in the real world. Therefore, our main focus and contribution is the ability to infer the preconditions and effects of actions based on a small number of demonstrations. Our system furthermore expresses the acquired manipulation actions as planning operators and is therefore able to use symbolic planners to solve new tasks. We implemented our approach on a PR2 robot and present real world manipulation experiments that illustrate that our system allows non-experts to transfer knowledge to robots.

Efficient motion planning for manipulation robots in environments with deformable objects

The ability to plan their own motions and to reliably execute them is an important precondition for autonomous robots. In this paper, we consider the problem of planning the motion of a mobile manipulation robot in the presence of deformable objects. Our approach combines probabilistic roadmap planning with a physical deformation simulation system. Since the physical deformation simulation is computationally demanding, we use efficient Gaussian process regression to estimate the deformation cost for individual objects based on training examples. We generate the training data by employing a simulation system in a preprocessing step. Consequently, no simulations are needed during runtime. We implemented and tested our approach on a mobile manipulation robot. Our experiments show that the robot is able to accurately predict and thus consider the deformation cost its manipulator introduces to the environment during motion planning. Simultaneously, the computation time is substantially reduced compared to a system that employs physical simulations online.

Robot, organize my shelves! Tidying up objects by predicting user preferences

As service robots become more and more capable of performing useful tasks for us, there is a growing need to teach robots how we expect them to carry out these tasks. However, learning our preferences is a nontrivial problem, as many of them stem from a variety of factors including personal taste, cultural background, or common sense. Obviously, such factors are hard to formulate or model a priori. In this paper, we present a solution for tidying up objects in containers, e.g., shelves or boxes, by following user preferences. We learn the user preferences using collaborative filtering based on crowdsourced and mined data. First, we predict pairwise object preferences of the user. Then, we subdivide the objects in containers by modeling a spectral clustering problem. Our solution is easy to update, does not require complex modeling, and improves with the amount of user data. We evaluate our approach using crowdsoucing data from over 1,200 users and demonstrate its effectiveness for two tidy-up scenarios. Additionally, we show that a real robot can reliably predict user preferences using our approach.

Organizing objects by predicting user preferences through collaborative filtering

As service robots become more and more capable of performing useful tasks for us, there is a growing need to teach robots how we expect them to carry out these tasks. However, different users typically have their own preferences, for example with respect to arranging objects on different shelves. As many of these preferences depend on a variety of factors including personal taste, cultural background, or common sense, it is challenging for an expert to pre-program a robot in order to accommodate all potential users. At the same time, it is impractical for robots to constantly query users about how they should perform individual tasks. In this work, we present an approach to learn patterns in user preferences for the task of tidying up objects in containers, e.g. shelves or boxes. Our method builds upon the paradigm of collaborative filtering for making personalized recommendations and relies on data from different users which we gather using crowdsourcing. To deal with novel objects for which we have no data, we propose a method that compliments standard collaborative filtering by leveraging information mined from the Web. When solving a tidy-up task, we first predict pairwise object preferences of the user. Then, we subdivide the objects in containers by modeling a spectral clustering problem. Our solution is easy to update, does not require complex modeling, and improves with the amount of user data. We evaluate our approach using crowdsourcing data from over 1200 users and demonstrate its effectiveness for two tidy-up scenarios. Additionally, we show that a real robot can reliably predict user preferences using our approach.

Inferring what to imitate in manipulation actions by using a recommender system.

Learning from demonstrations is an intuitive way for instructing robots by non-experts. One challenge in learning from demonstrations is to infer what to imitate, especially when the robot only observes the teacher and does not have further knowledge about the demonstrated actions. In this paper, we present a novel approach to the problem of inferring what to imitate to successfully reproduce a manipulation action based on a small number of demonstrations. Our method employs techniques from recommender systems to include expert knowledge. It models the demonstrated actions probabilistically and formulates the problem of inferring what to imitate via model selection. We select an appropriate model for the action each time the robot has to reproduce it given a new starting condition. We evaluate our approach using data acquired with a PR2 robot and demonstrate that our method achieves high success rates in different scenarios.

Sensor fusion in the epistemic situation calculus

Robot sensors are usually subject to error. Since in many practical scenarios a probabilistic error model is not available, sensor readings are often dealt with in a hard-coded, heuristic fashion. In this paper, we propose a logic to address the problem from a KR perspective. In this logic, the epistemic effect of sensing actions is deferred to so-called fusion actions, which may resolve discrepancies and inconsistencies of recent sensing results. Moreover, a local closed-world assumption can be applied dynamically. When needed, this assumption can be revoked and fusions can be undone using a form of forgetting.