Human-robot co-manipulation of soft materials, such as fabrics, composites, and sheets of paper/cardboard, is a challenging operation that presents several relevant industrial applications. Estimating the deformation state of the co-manipulated material is one of the main challenges. Viable methods provide the indirect measure by calculating the human-robot relative distance. In this paper, we develop a data-driven model to estimate the deformation state of the material from a depth image through a Convolutional Neural Network (CNN). First, we define the deformation state of the material as the relative roto-translation from the current robot pose and a human grasping position. The model estimates the current deformation state through a Convolutional Neural Network, specifically a DenseNet-121 pretrained on ImageNet.The delta between the current and the desired deformation state is fed to the robot controller that outputs twist commands. The paper describes the developed approach to acquire, preprocess the dataset and train the model. The model is compared with the current state-of-the-art method based on a skeletal tracker from cameras. Results show that our approach achieves better performances and avoids the various drawbacks caused by using a skeletal tracker.Finally, we also studied the model performance according to different architectures and dataset dimensions to minimize the time required for dataset acquisition

This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The system achieves much of its power by transferring parts of previously learned solutions rather than a single complete solution. The system exploits strong features in the multi-dimensional function produced by reinforcement learning in solving a particular task. These features are stable and easy to recognize early in the learning process. They generate a partitioning of the state space and thus the function. The partition is represented as a graph. This is used to index and compose functions stored in a case base to form a close approximation to the solution of the new task. Experiments demonstrate that function composition often produces more than an order of magnitude increase in learning rate compared to a basic reinforcement learning algorithm.

We describe and evaluate the algorithmic techniques that are used in the FF planning system. Like the HSP system, FF relies on forward state space search, using a heuristic that estimates goal distances by ignoring delete lists. Unlike HSP's heuristic, our method does not assume facts to be independent. We introduce a novel search strategy that combines hill-climbing with systematic search, and we show how other powerful heuristic information can be extracted and used to prune the search space. FF was the most successful automatic planner at the recent AIPS-2000 planning competition. We review the results of the competition, give data for other benchmark domains, and investigate the reasons for the runtime performance of FF compared to HSP.

In this paper we realize the synthesis of continuous coordinations By envisaging standards to publish and access services over based on the conceptual framework of (Pistore, the Web, the Service-Oriented Computing (SOC) paradigm Traverso, and Bertoli 2005), which recasts the composition promises a novel degree of interoperability between distributed problem in terms of planning; namely, we act at its core applications that realize business processes. One by adopting a very simple, yet expressive requirements language, cornerstone of SOC stands in the provision of novel and and devising a novel planning algorithm. In particular, more complex business logics by the coordination of existing the requirement language expresses coordination constraints services. Due to the complexity of manually realizing that are transformed into preference-ordered maintenability such coordinations, automatedly supporting the synthesis goals, and the algorithm deals with such goals in of service orchestrations is crucial to the actual enactment the presence of exogenous events (which encode independent of SOC. This problem is extremely hard since, asynchronous evolutions of services).