Abstract-Placing is a necessary skill for a personal robot to have in order to perform tasks such as arranging objects in a disorganized room. The object placements should not only be stable but also be in their semantically preferred placing areas and orientations. This is challenging because an environment can have a large variety of objects and placing areas that may not have been seen by the robot before.In this paper, we propose a learning approach for placing multiple objects in different placing areas in a scene. Given point-clouds of the objects and the scene, we design appropriate features and use a graphical model to encode various properties, such as the stacking of objects, stability, object-area relationship and common placing constraints. The inference in our model is an integer linear program, which we solve efficiently via an LP relaxation. We extensively evaluate our approach on 98 objects from 16 categories being placed into 40 areas. Our robotic experiments show a success rate of 98% in placing known objects and 82% in placing new objects stably. We use our method on our robots for performing tasks such as loading several dish-racks, a bookshelf and a fridge with multiple items.

Abstract-The ability to place objects in an environment is an important skill for a personal robot. An object should not only be placed stably, but should also be placed in its preferred location/orientation. For instance, it is preferred that a plate be inserted vertically into the slot of a dish-rack as compared to being placed horizontally in it. Unstructured environments such as homes have a large variety of object types as well as of placing areas. Therefore our algorithms should be able to handle placing new object types and new placing areas. These reasons make placing a challenging manipulation task.In this work, we propose using supervised learning approach for finding good placements given the point clouds of the object and the placing area. It learns to combine the features that capture support, stability and preferred placements using a shared sparsity structure in the parameters. Even when neither the object nor the placing area is seen previously in the training set, our algorithm predicts good placements. In extensive experiments, our method enables the robot to stably place several new objects in several new placing areas with a 98% success-rate, and it placed the objects in their preferred placements in 92% of the cases.

Criminal network activities, which are usually secret and stealthy, present certain difficulties in conducting criminal network analysis (CNA) because of the lack of complete datasets. The collection of criminal activities data in these networks tends to be incomplete and inconsistent, which is reflected structurally in the criminal network in the form of missing nodes (actors) and links (relationships). Criminal networks are commonly analyzed using social network analysis (SNA) models. Most machine learning techniques that rely on the metrics of SNA models in the development of hidden or missing link prediction models utilize supervised learning. However, supervised learning usually requires the availability of a large dataset to train the link prediction model in order to achieve an optimum performance level. Therefore, this research is conducted to explore the application of deep reinforcement learning (DRL) in developing a criminal network hidden links prediction model from the reconstruction of a corrupted criminal network dataset. The experiment conducted on the model indicates that the dataset generated by the DRL model through self-play or self-simulation can be used to train the link prediction model. The DRL link prediction model exhibits a better performance than a conventional supervised machine learning technique, such as the gradient boosting machine (GBM) trained with a relatively smaller domain dataset.

No abstract

The prediction of hidden or missing links in a criminal network, which represent possible interactions between individuals, is a significant problem. The criminal network prediction models commonly rely on Social Network Analysis (SNA) metrics. These models leverage on machine learning (ML) techniques to enhance the predictive accuracy of the models and processing speed. The problem with the use of classical ML techniques such as support vector machine (SVM), is the dependency on the availability of large dataset for training purpose. However, recent ground breaking advances in the research of deep reinforcement learning (DRL) techniques have developed methods of training ML models through self-generated dataset. In view of this, DRL could be applied to other domains with relatively smaller dataset such as criminal networks. Prior to this research, few, if any, previous works have explored the prediction of links within criminal networks that could appear and/or disappear over time by leveraging on DRL technique. Therefore, in this paper, the primary objective is to construct a time-based link prediction model (TDRL) by leveraging on DRL technique to train using a relatively small real-world criminal dataset that evolves over time. The experimental results indicate that the predictive accuracy of the DRL model trained on the temporal dataset is significantly better than other ML models that are trained only with the dataset at specific snapshot in time. INDEX TERMS Social network analysis, link prediction performance, deep reinforcement learning, time-evolving network.