Search

Imitation learning is a methodology, which trains an agent using demonstrations from skilled experts without external rewards. However, for a complex task with a long horizon, it is challenging to obtain data that exactly match the desired task. In general, humans can easily assign a sequence of simple tasks for performing complex tasks. If a person gives an agent an order of simple tasks to carry out a complex task, we can find a skill sequence efficiently by learning the corresponding skills. However, independently trained low-level skills (simple tasks) are incompatible, so they cannot be performed in sequence without additional refinement. In this context, we propose a method to create a skill chain by connecting independently learned skills. For connecting two consecutive low-level policies, we need to find a new policy defined as a bridge skill. To train a bridge skill, a well-designed reward function is required, but in real world, only sparse rewards can be given according to the success of the overall task. To complement this issue, we introduce a novel latent-distance reward function from fragmented demonstrations. Also, we use binary classifiers to determine whether the current state is capable of performing the skill that follows. As a result, the skill chain formed from incomplete demonstrations can successfully perform complex tasks which require performing multiple skills in a sequence. In the experiment, we solve manipulation tasks with RGBD images as input in the Baxter simulator implemented using MuJoCo. We verify that skill chains can be successfully trained from incomplete data while confirming that the agent can be trained much more efficiently and stably through the proposed latent-distance rewards. Also, we perform block stacking using a real Baxter robot in the simple set-up environment. [ABSTRACT FROM AUTHOR]

We present a robust target tracking algorithm for a mobile robot. It is assumed that a mobile robot carries a sensor with a fan-shaped field of view and finite sensing range. The goal of the proposed tracking algorithm is to minimize the probability of losing a target. If the distribution of the next position of a moving target is available as a Gaussian distribution from a motion prediction algorithm, the proposed algorithm can guarantee the tracking success probability. In addition, the proposed method minimizes the moving distance of the mobile robot based on the chosen bound on the tracking success probability. While the considered problem is a non-convex optimization problem, we derive a closed-form solution when the heading is fixed and develop a real-time algorithm for solving the considered target tracking problem. We also present a robust target tracking algorithm for aerial robots in 3D. The performance of the proposed method is evaluated extensively in simulation. The proposed algorithm has been successful applied in field experiments using Pioneer mobile robot with a Microsoft Kinect sensor for following a pedestrian. [ABSTRACT FROM AUTHOR]

Recovering the 3D shape of a non-rigid object is a challenging problem. Existing methods make the low-rank assumption and do not scale well with the increased degree of freedom found in complex non-rigid deformations or shape variations. Moreover, in general, the degree of freedom of deformation is assumed to be known in advance, which limits the applicability of non-rigid structure from motion algorithms in a practical situation. In this paper, we propose a method for handling complex shape variations based on the assumption that complex shape variations can be represented probabilistically by a mixture of primitive shape variations. The proposed model is a generative probabilistic model, called a Procrustean normal distribution mixture model, which can model complex shape variations without rank constraints. Experimental results show that the proposed method significantly outperforms existing methods. [ABSTRACT FROM AUTHOR]

With various sensors in a smartphone, it is now possible to obtain information about a user and her surroundings, such as the location and the activity of the smartphone user, and the obtained context information is being used to provide new services to the users. In this paper, we propose VibePhone, which uses a built-in vibrator and accelerometer, for efficiently recognizing the type of surfaces contacted by a smartphone, enabling the sense of touch to smartphones. In particular, this paper focuses on developing a succinct set of features that are useful for recognizing surface types for reducing computation and memory requirements, which will in turn reduce the power consumption of the device. For humans and animals, the sense of touch, which is obtained from the texture of an object by scrubbing its surface, is fundamental for both recognizing and learning the properties of objects. Since a smartphone cannot physically scrub the contacting surface, we emulate the touch by generating vibrations and analyzing accelerometer readings. While the recognition of the object type by vibration alone is an extremely difficult task, even for a human, we demonstrate that it is possible to distinguish object types into broad categories where a phone is usually placed. For efficiency, VibePhone uses only a small subset of the most informative features of accelerometer readings using feature selection and reduces the computation time by 92 % using only 15 % of features, while maintaining performance. We believe that our analysis of vibrations about contacted surfaces can provide an important insight for the haptic perception in future smartphones, enabling new experiences to the users. [ABSTRACT FROM AUTHOR]

A smart space, which is embedded with networked sensors and smart devices, can provide various useful services to its users. For the success of a smart space, the problem of tracking and identification of smart space users is of paramount importance. We propose a system, called Optimus, for persistent tracking and identification of users in a smart space, which is equipped with a camera network. We assume that each user carries a smartphone in a smart space. A camera network is used to solve the problem of tracking multiple users in a smart space and information from smartphones is used to identify tracks. For robust tracking, we first detect human subjects from images using a head detection algorithm based on histograms of oriented gradients. Then, human detections are combined to form tracklets and delayed track-level association is used to combine tracklets to build longer trajectories of users. Last, accelerometers in smartphones are used to disambiguate identities of trajectories. By linking identified trajectories, we show that the average length of a track can be lengthened by over six times. The performance of the proposed system is evaluated extensively in realistic scenarios. [ABSTRACT FROM AUTHOR]

In this paper, we present a personal area situation understanding (PASU) system, a novel application of a smart device using wireless camera sensor networks. The portability of a PASU system makes it an attractive solution for monitoring and understanding the current situation of the personal area around a user. The PASU system allows its user to construct a 3D scene of the environment and view the scene from various vantage points for better understanding of the environment. The paper describes the architecture and implementation of the PASU system addressing limitations of wireless camera sensor networks, such as low bandwidth and limited computational capabilities. The capabilities of PASU are validated with extensive experiments. The PASU system demonstrates the potential of a portable system combining a smart device and a wireless camera sensor network for personal area monitoring and situation understanding. [ABSTRACT FROM AUTHOR]