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]

Much progress has been made for non-rigid structure from motion (NRSfM) during the last two decades, which made it possible to provide reasonable solutions for synthetically-created benchmark data. In order to utilize these NRSfM techniques in more realistic situations, however, we are now facing two important problems that must be solved: First, general scenes contain complex deformations as well as multiple objects, which violates the usual assumptions of previous NRSfM proposals. Second, there are many unreconstructable regions in the video, either because of the discontinued tracks of 2D trajectories or those regions static towards the camera, which require careful manipulations. In this paper, we show that a consensus-based reconstruction framework can handle these issues effectively. Even though the entire scene is complex, its parts usually have simpler deformations, and even though there are some unreconstructable parts, they can be weeded out to reduce their harmful effect on the entire reconstruction. The main difficulty of this approach lies in identifying appropriate parts, however, it can be effectively avoided by sampling parts stochastically and then aggregate their reconstructions afterwards. Experimental results show that the proposed method renews the state-of-the-art for popular benchmark data under much harsher environments, i.e., narrow camera view ranges, and it can reconstruct video-based real-world data effectively for as many areas as it can without an elaborated user input. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the problem of learning from demonstration (LfD) where demonstrations with different proficiencies are provided without labeling. To this end, we model multiple policies with different qualities as correlated Gaussian processes and present a leverage optimization method that estimates the leverage of each policy where the difference between two leverages defines the correlation between the corresponding policies. To recover a single policy function of an expert, we present a sparsity constraint on the leverage parameters. We first show that the proposed leverage optimization method can recover the correlations between sensory fields where the fields are realized from correlated Gaussian processes and sensor measurements are collected from the fields. Furthermore, we applied the proposed method to autonomous driving experiments, where demonstrations are collected from three different driving modes. While the driving policies are not realized from correlated processes, the proposed method assigns reasonable leverages to the driving demonstrations. The estimated driving policy of an expert, which incorporates the optimized leverages, outperforms previous LfD methods in terms of both safety and driving quality. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of estimating the head pose and body orientation of a person from a low-resolution image. Under this setting, it is difficult to reliably extract facial features or detect body parts. We propose a convolutional random projection forest (CRPforest) algorithm for these tasks. A convolutional random projection network (CRPnet) is used at each node of the forest. It maps an input image to a high-dimensional feature space using a rich filter bank. The filter bank is designed to generate sparse responses so that they can be efficiently computed by compressive sensing. A sparse random projection matrix can capture most essential information contained in the filter bank without using all the filters in it. Therefore, the CRPnet is fast, e.g., it requires $0.04\;\mathrm{ms}$ to process an image of $50\times 50$ pixels, due to the small number of convolutions (e.g., 0.01 percent of a layer of a neural network) at the expense of less than 2 percent accuracy. The overall forest estimates head and body pose well on benchmark datasets, e.g., over 98 percent on the HIIT dataset, while requiring $3.8\;\mathrm{ms}$ without using a GPU. Extensive experiments on challenging datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in low-resolution images with noise, occlusion, and motion blur. [ABSTRACT FROM AUTHOR]

This paper considers two important problems for autonomous robot navigation in a dynamic environment, where the goal is to predict pedestrian motion and control a robot with the prediction for safe navigation. While there are several methods for predicting the motion of a pedestrian and controlling a robot to avoid incoming pedestrians, it is still difficult to safely navigate in a dynamic environment due to challenges, such as the varying quality and complexity of training data with unwanted noises. This paper addresses these challenges simultaneously by proposing a robust kernel subspace learning algorithm based on the recent advances in nuclear-norm and l1-norm minimization. We model the motion of a pedestrian and the robot controller using Gaussian processes. The proposed method efficiently approximates a kernel matrix used in Gaussian process regression by learning low-rank structured matrix (with symmetric positive semi-definiteness) to find an orthogonal basis, which eliminates the effects of erroneous and inconsistent data. Based on structured kernel subspace learning, we propose a robust motion model and motion controller for safe navigation in dynamic environments. We evaluate the proposed robust kernel learning in various tasks, including regression, motion prediction, and motion control problems, and demonstrate that the proposed learning-based systems are robust against outliers and outperform existing regression and navigation methods. [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]

This paper presents a cost-effective motion-planning method for robots operating in complex and realistic environments. While sampling-based path-planning algorithms, such as a rapidly exploring random tree (RRT) and its variants, have been highly effective for general path-planning problems, it is still difficult to find the minimum cost path in a complex space efficiently since RRT-based algorithms extend a search tree locally, requiring a large number of samples before finding a good solution. This paper presents an efficient nonmyopic path-planning algorithm by combining RRT* and a stochastic optimization method, called cross entropy. The proposed method constructs two RRT trees: The first tree is a standard RRT* tree, which is used to determine the nearest node in the tree to be extended to a randomly chosen point, and the second tree contains the first tree with additional long extensions. By maintaining two separate trees, we can grow the search tree nonmyopically to improve the efficiency of the algorithm while ensuring the asymptotic optimality of RRT*. From an extensive set of simulations and experiments using mobile and humanoid robots, we demonstrate that the proposed method consistently finds low-cost paths faster than the existing algorithms. [ABSTRACT FROM PUBLISHER]

A well-defined deformation model can be vital for non-rigid structure from motion (NRSfM). Most existing methods restrict the deformation space by assuming a fixed rank or smooth deformation, which are not exactly true in the real world, and they require the degree of deformation to be predetermined, which is impractical. Meanwhile, the errors in rotation estimation can have severe effects on the performance, i.e., these errors can make a rigid motion be misinterpreted as a deformation. In this paper, we propose an alternative to resolve these issues, motivated by an observation that non-rigid deformations, excluding rigid changes, can be concisely represented in a linear subspace without imposing any strong constraints, such as smoothness or low-rank. This observation is embedded in our new prior distribution, the Procrustean normal distribution (PND), which is a shape distribution exclusively for non-rigid deformations. Because of this unique characteristic of the PND, rigid and non-rigid changes can be strictly separated, which leads to better performance. The proposed algorithm, EM-PND, fits a PND to given 2D observations to solve NRSfM without any user-determined parameters. The experimental results show that EM-PND gives the state-of-the-art performance for the benchmark data sets, confirming the adequacy of the new deformation model. [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]

In this paper, we propose a coordinated localization algorithm for mobile sensor networks with camera sensors to operate under Global Positioning System (GPS) denied areas or indoor environments. Mobile robots are partitioned into two groups. One group moves within the field of views of remaining stationary robots. The moving robots are tracked by stationary robots and their trajectories are used as spatiotemporal features. From these spatiotemporal features, relative poses of robots are computed using multiview geometry and a group of robots is localized with respect to the reference coordinate based on the proposed multirobot localization. Once poses of all robots are recovered, a group of robots moves from one location to another while maintaining the formation of robots for coordinated localization under the proposed multirobot navigation strategy. By taking the advantage of a multiagent system, we can reliably localize robots over time as they perform a group task. In experiment, we demonstrate that the proposed method consistently achieves a localization error rate of 0.37% or less for trajectories of length between 715~cm and 890~cm using an inexpensive off-the-shelf robotic platform. [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]

In this paper, we consider mobile sensor networks that use spatiotemporal Gaussian processes to predict a wide range of spatiotemporal physical phenomena. Nonparametric Gaussian process regression that is based on truncated observations is proposed for mobile sensor networks with limited memory and computational power. We first provide a theoretical foundation of Gaussian process regression with truncated observations. In particular, we demonstrate that prediction using all observations can be well approximated by prediction using truncated observations under certain conditions. Inspired by the analysis, we then propose a centralized navigation strategy for mobile sensor networks to move in order to reduce prediction error variances at points of interest. For the case in which each agent has a limited communication range, we propose a distributed navigation strategy. Particularly, we demonstrate that mobile sensing agents with the distributed navigation strategy produce an emergent, swarming-like, collective behavior for communication connectivity and are coordinated to improve the quality of the collective prediction capability. [ABSTRACT FROM AUTHOR]

This paper presents recent advances in multiagent sensing and operation in dynamic environments. Technology trends point towards a fusion of wireless sensor networks with robotic swarms of mobile robots. In this paper, we discuss the coordination and collaboration between networked robotic systems, featuring algorithms for cooperative operations such as unmanned aerial vehicles (UAVs) swarming. We have developed cooperative actions of groups of agents such as probabilistic pursuit-evasion game for search and rescue operations, protection of resources, and security applications. We have demonstrated a hierarchical system architecture which provides wide-range sensing capabilities to unmanned vehicles through spatially deployed wireless sensor networks, highlighting the potential collaboration between wireless sensor networks and unmanned vehicles. This paper also includes a short review of our current research efforts in heterogeneous sensor networks, which is being evolved into mobile sensor networks with swarm mobility. In a very essential way, this represents the fusion of mobility of ensembles with the network embedded systems, the robotic sensor web. [ABSTRACT FROM PUBLISHER]

Compound eyes, also known as insect eyes, have a unique structure. They have a hemispheric surface, and a lot of single eyes are deployed regularly on the surface. Thanks to this unique form, using the compound images has several advantages, such as a large field of view (FOV) with low aberrations. We can exploit these benefits in high-level vision applications, such as object recognition, or semantic segmentation for a moving robot, by emulating the compound images that describe the captured scenes from compound eye cameras. In this paper, to the best of our knowledge, we propose the first convolutional neural network (CNN)-based ego-motion classification algorithm designed for the compound eye structure. To achieve this, we introduce a voting-based approach that fully utilizes one of the unique features of compound images, specifically, the compound images consist of a lot of single eye images. The proposed method classifies a number of local motions by CNN, and these local classifications which represent the motions of each single eye image, are aggregated to the final classification by a voting procedure. For the experiments, we collected a new dataset for compound eye camera ego-motion classification which contains scenes of the inside and outside of a certain building. The samples of the proposed dataset consist of two consequent emulated compound images and the corresponding ego-motion class. The experimental results show that the proposed method has achieved the classification accuracy of 85.0%, which is superior compared to the baselines on the proposed dataset. Also, the proposed model is light-weight compared to the conventional CNN-based image recognition algorithms such as AlexNet, ResNet50, and MobileNetV2. [ABSTRACT FROM AUTHOR]