Purpose-In this paper we propose a method for learning robotic assembly sequences, where precedence constraints and object relative size and location constraints can be learned by demonstration and autonomous robot exploration. Design/methodology/approach-In order to successfully plan the operations involved in assembly tasks, the planner needs to know the constraints of the desired task. In this paper we propose a methodology for learning such constraints by demonstration and autonomous exploration. We investigated the learning of precedence constraints and object relative size and location constraints, which are needed to construct a planner for automated assembly. In the developed system, the learning of symbolic constraints is integrated with low-level control algorithms, which is essential to enable active robot learning. Findings-We demonstrated that the proposed reasoning algorithms can be used to learn previously unknown assembly constraints that are needed to implement a planner for automated assembly. Cranfield benchmark, which is a standardized benchmark for testing algorithms for robot assembly, was used to evaluate the proposed approaches. We evaluated the learning performance both in simulation and on a real robot. Practical implications (if applicable)-Our approach reduces the amount of programming that is needed to set up new assembly cells and consequently the overall set up time when new products are introduced into the workcell. Originality/value-In this paper we propose a new approach for learning assembly constraints based on programming by demonstration and active robot exploration to reduce the computational complexity of the underlying search problems. We developed algorithms for success/failure detection of assembly operations based on the comparison of expected signals (forces and torques, positions and orientations of the assembly parts) with the actual signals sensed by a robot. In this manner all precedence and object size and location constraints can be learned, thereby providing the necessary input for the optimal planning of the entire assembly process.

No abstract

In practice, an incomplete heuristic search nearly always finds better solutions if it is allowed to search deeper, i.e., expand and heuristically evaluate more nodes in the search tree. On the rare occasions when searching deeper is not beneficial, a curious phenomenon called "search pathology" occurs. In this paper we study the pathology and gain of a deeper search of the minimin algorithm in the 8-puzzle, a domain often used for evaluating single-agent search algorithms. We have analyzed the influence of various properties of the search tree and the heuristic evaluation function on the gain and the pathology. In order to investigate a broad range of the properties, the original 8-puzzle was extended with diagonal moves, yielding a larger variety of search trees. It turned out that in the 8-puzzle a substantial proportion of the solvable positions is pathological under various parameters. More importantly, the search parameters that enable the highest gains are quite consistent in pathological and non-pathological positions alike, thus pointing to potentially successful search strategies.

No abstract

The paper describes an approach for recognizing a person entering a room using only door accelerations. The approach analyzes the acceleration signal in time and frequency domain. For each domain two types of methods were developed: (i) feature-baseduse features to describe the acceleration and then uses classification method to identify the person; (ii) signal-baseduse the acceleration signal as input and finds the most similar ones in order to identify the person. The four methods were evaluated on a dataset of 1005 entrances recorded by 12 people. The results show that the time-domain methods achieve significantly higher accuracy compared to the frequency-domain methods, with signalbased method achieving 86% accuracy. Additionally, the four methods were combined and all 15 combinations were examined. The best performing combined method increased the accuracy to 90%. The results confirm that it is possible to identify a person entering a room using the door's acceleration.

No abstract

Comprehensibility is the decisive factor for application of classifiers in practice. However, most algorithms that learn comprehensible classifiers use classification model size as a metric that guides the search in the space of all possible classifiers instead of comprehensibility -which is ill-defined. Several surveys have shown that such simple complexity metrics do not correspond well to the comprehensibility of classification trees. This paper therefore suggests a classification tree comprehensibility survey in order to derive an exhaustive comprehensibility metrics better reflecting the human sense of classifier comprehensibility and obtain new insights about comprehensibility of classification trees.

No abstract