IROS 2018 论文列表

Dense mapping is always the desire of simultaneous localization and mapping (SLAM), especially for the applications that require fast and dense scene information. Visual-inertial odometry (VIO) is a light-weight and effective solution to fast self-localization. However, VIO-based SLAM systems have difficulty in providing dense mapping results due to the spatial sparsity and temporal instability of the VIO depth estimations. Although there have been great efforts on real-time mapping and depth recovery from sparse measurements, the existing solutions for VIO-based SLAM still fail to preserve sufficient geometry details in their results. In this paper, we propose to embed depth recovery into VIO-based SLAM for real-time dense mapping. In the proposed method, we present a subspace-based stabilization scheme to maintain the temporal consistency and design a hierarchical pipeline for edge-preserving depth interpolation to reduce the computational burden. Numerous experiments demonstrate that our method can achieve an accuracy improvement of up to 49.1 cm compared to state-of-the-art learning-based methods for depth recovery and reconstruct sufficient geometric details in dense mapping when only 0.07% depth samples are available. Since a simple CPU implementation of our method already runs at 10-20 fps, we believe our method is very favorable for practical SLAM systems with critical computational requirements.

Research focusing on the development of socially assistive robots (SARs) for the care of older adults has grown in recent years, prompting a great deal of ethical analysis and reflection on the future of SARs in caring roles. Much of this ethical thinking, however, has taken place far from the settings where technological innovation is practiced. Different frameworks have been proposed to bridge this gap and enable researchers to handle the ethical dimension of technology from within the design and development process, including Value Sensitive Design (VSD). VSD has been defined as a “theoretically grounded approach to the design of technology that accounts for human values in a principled and comprehensive manner throughout the design process”. Inspired in part by VSD, we have developed a process geared towards embedding ethics at the core of CARESSES, an international multidisciplinary project that aims to design the first culturally competent SAR for the care of older adults. Here we describe that process, which included extracting key ethical concepts from relevant ethical guidelines and applying those concepts to scenarios that describe how the CARESSES robot will interact with individuals belonging to different cultures. This approach highlights the ethical implications of the robot's behavior early in the design process, thus enabling researchers to identify and engage with ethical problems proactively.

Shape morphing, meaning a structure can first morph and then lock into another shape, can be applied to robot designs to endow robots with adaptive morphology for increased functionality and adaptivity. In this paper, we introduce a novel shape morphing scheme enabled by a new artificial muscle: twisted and coiled actuators (TCAs). This new actuator is purely soft, low cost, and electrically driven. Embedding a TCA and a thermoplastic material with variable stiffness into soft materials, we create a miniature shape-morphing link. We also establish a general model to predict the steady-state shape of the link given an input power applied to the TCA. Experiments are conducted to characterize parameters and verify the proposed model. Finally, we demonstrate this shape-morphing link can serve as a link in a mechanism to change the trajectory of its foot or endpoint. We envision that such a new shape-morphing scheme can enable robots to leverage the same mechanical design for different functions.

Among the diversity of the existing modular robotic systems, we consider in this paper the subset of distributed modular robotic ensembles composed of resource-constrained identical modules that are organized in a lattice structure and which can only communicate with neighboring modules. These modular robotic ensembles form asynchronous distributed embedded systems. In many algorithms dedicated to distributed system coordination, a specific role has to be played by a leader, i.e., a single node in the system. This leader can be elected using various criteria. A possible strategy is to elect a center node, i.e., a node that has the minimum distance to all the other nodes. Indeed, this node is ideally located to communicate with all the others and this leads to better performance in many algorithms. The contribution of this paper is to propose the k-BFS SumSweep algorithm designed to elect an approximate-center node. We evaluated our algorithm both on hardware modular robots and in a simulator for large ensembles of robots. Experimental results show that k-BFS SumSweep is often the most accurate approximation algorithm (with an average relative accuracy between 90% to 100%) while using the fewest messages in large-scale systems, requiring only a modest amount of memory per node, and converging in a reasonable length of time.

We present a new approach for Cartesian impedance control of compliantly actuated robots with possibly nonlinear spring characteristics. It reveals a remarkable stiffness and damping range in the experimental evaluation. The most interesting contribution, is the way the desired closed-loop dynamics is designed. Our control concept allows to add a desired stiffness and damping directly on the end-effector, while leaving the system structure intact. The intrinsic inertial and elastic properties of the system are preserved. This is achieved by introducing new motor coordinates that reflect the desired spring and damper terms. Theoretically, by means of additional motor inertia shaping it is possible to make the end-effector interaction behavior with respect to external loads approach, arbitrarily close, the interaction behavior that is achievable by classical Cartesian impedance control on rigid robots. The physically motivated design approach allows for an intuitive understanding of the resulting closed-loop dynamics. We perform a passivity and stability analysis on the basis of al physically motivated storage and Lyapunov function.

Egocentric spatial memory (ESM) defines a memory system with encoding, storing, recognizing and recalling the spatial information about the environment from an egocentric perspective. We introduce an integrated deep neural network architecture for modeling ESM. It learns to estimate the occupancy state of the world and progressively construct top-down 2D global maps from egocentric views in a spatially extended environment. During the exploration, our proposed ESM model updates belief of the global map based on local observations using a recurrent neural network. It also augments the local mapping with a novel external memory to encode and store latent representations of the visited places over longterm exploration in large environments which enables agents to perform place recognition and hence, loop closure. Our proposed ESM network contributes in the following aspects: (1) without feature engineering, our model predicts free space based on egocentric views efficiently in an end-to-end manner; (2) different from other deep learning-based mapping system, ESMN deals with continuous actions and states which is vitally important for robotic control in real applications. In the experiments, we demonstrate its accurate and robust global mapping capacities in 3D virtual mazes and realistic indoor environments by comparing with several competitive baselines.

Visual odometry methods are increasingly being used to estimate a vehicle's ego-motion from range data due to the decreasing cost of range sensors and the impressive speed and accuracy of visual odometry techniques. Dense geometry-based visual odometry methods are fundamentally based on the range flow constraint equation, an equation which depends on the temporal and spatial derivatives of range images. However, these derivatives are calculated with the fundamental assumption that the range flow is magnitude-limited. When scaling this method for faster vehicles, this assumption could be violated, invaliding the range flow constraint equation and thus corrupting the resulting ego-motion estimates. This paper derives the sensor, motion, environment, and sampling frequency conditions that would mathematically violate the range flow constraint. This information is useful for defining the operational limits of dense geometry-based visual odometry methods.

Motion planners have been recently developed that provide path quality guarantees for robots with dynamics. This work aims to improve upon their efficiency, while maintaining their properties. Inspired by informed search principles, one objective is to use heuristics. Nevertheless, comprehensive and fast spatial exploration of the state space is still important in robotics. For this reason, this work introduces Dominance-Informed Regions (DIR), which express both whether parts of the space are unexplored and whether they lies along a high quality path. Furthermore, to speed up the generation of a successful successor state, which involves collision checking or physics-based simulation, a proposed strategy generates the most promising successor in an informed way, while maintaing properties. Overall, this paper introduces a new informed and asymptotically optimal kinodynamic motion planner, the Dominance-Informed Region Tree (DIRT). The method balances exploration-exploitation tradeoffs without many explicit parameters. It is shown to outperform sampling-based and search-based methods for robots to significant dynamics.

Due to the limitations of the robotic sensors, during a robotic manipulation task, the acquisition of the object's state can be unreliable and noisy. Combining an accurate model of multi-body dynamic system with Bayesian filtering methods has been shown to be able to filter out noise from the object's observed states. However, efficiency of these filtering methods suffers from samples that violate the physical constraints, e.g., no penetration constraint. In this paper, we propose a Rao-Blackwellized Particle Filter (RBPF) that samples the contact states and updates the object's poses using Kalman filters. This RBPF also enforces the physical constraints on the samples by solving a quadratic programming problem. By comparing our method with methods that does not consider physical constraints, we show that our proposed RBPF is not only able to estimate the object's states, e.g., poses, more accurately but also able to infer unobserved states, e.g., velocities, with higher precision.

We propose a high efficient learning approach to estimating 6D (Degree of Freedom) pose of the textured or texture-less objects for grasping purposes in a cluttered environment where the objects might be partially occluded. The method comprises three main steps. Given a single RGB-D image, we first deploy appropriate features and the random forest to deduce the object class probability and cast votes for the 6D pose in Hough space by joint regression and classification framework, adopting reservoir sampling and summarizing the pose distribution by clustering. Next, we integrate the auto-context into cascaded Hough forests to improve the efficiency of learning. Extensive experiments on various public datasets and robotic grasps indicate that our method presents some improvements over the state-of-art and reveals the capability for estimating poses in practical applications efficiently.

This paper aims to identify in a practical manner unknown physical parameters, such as mechanical models of actuated robot links, which are critical in dynamical robotic tasks. Key features include the use of an off-the-shelf physics engine and the Bayesian optimization framework. The task being considered is locomotion with a high-dimensional, compliant Tensegrity robot. A key insight, in this case, is the need to project the space of models into an appropriate lower dimensional space for time efficiency. Comparisons with alternatives indicate that the proposed method can identify the parameters more accurately within the given time budget, which also results in more precise locomotion control.

Efficient 2D and 3D map representations of both static and dynamic, indoor and outdoor environments are crucial for navigation of driving and flying robots. In this paper, we propose a fast and accurate approach for 2D and 3D Normal Distributions Transform (NDT) mapping based on indexed kd-trees. Similar to other approaches, we also model free space, which allows us to obtain occupancy probabilities. Additionally, we provide optional visibility based updates to enhance map consistency in case of noisy data, e.g. from stereo cameras. Unlike other available implementations, our approach is natively applicable to large-scale environments and in real-time, because our maps are able to grow dynamically. This also offers applicability to exploration tasks. To evaluate our approach, we present experimental results on publicly available datasets and discuss the mapping efficiency in terms of accuracy, runtime and memory management. As an exemplary use case, we apply our maps to Monte Carlo Localization on a well-known large-scale dataset.

As autonomous robots are increasingly being introduced in real-world environments operating for long periods of time, the difficulties of long-term mapping are attracting the attention of the robotics research community. This paper proposes a full SLAM system capable of handling the dynamics of the environment across a single or multiple mapping sessions. Using the pose graph SLAM paradigm, the system works on local maps in the form of 2D point cloud data which are updated over time to store the most up-to-date state of the environment. The core of our system is an efficient ICP-based alignment and merging procedure working on the clouds that copes with non-static entities of the environment. Furthermore, the system retains the graph complexity by removing out-dated nodes upon robust inter- and intra-session loop closure detections while graph coherency is preserved by using condensed measurements. Experiments conducted with real data from longterm SLAM datasets demonstrate the efficiency, accuracy and effectiveness of our system in the management of the mapping problem during long-term robot operation.

The realization of a kinesthetic robot behavior using robot skin requires a reactive skin torque controller, which fuses skin information and robot information to an appropriate skin joint torque in real-time. This fusion of information in real-time is challenging when deploying large scale skin. In this paper, we present a system which efficiently computes the torque of distributed skin cells locally at the point of contacts, completely removing this complex computations from the real-time loop. We demonstrate the feasibility of realizing the skin joint torque computations on the local micro-controllers of the skin cells. Conducting experiments with a real robot, we compare the accuracy of the distributed skin joint torque computation with the computation on the control PC. We also show that the novel distributed approach completely eliminates the computational delay of computing skin joint torques in the robot's real-time control loop. As a result, this approach removes any limits for the maximum number of skin cells in control.

Safe motion planning requires that a vehicle reaches a set of safe states at the end of the planning horizon. However, safe states of vehicles have not yet been systematically defined in the literature, nor does a computationally efficient way to obtain them for online motion planning exist. To tackle the aforementioned issues, we introduce invariably safe sets. These are regions that allow vehicles to remain safe for an infinite time horizon. We show how invariably safe sets can be computed and propose a tight under-approximation which can be obtained efficiently in linear time with respect to the number of traffic participants. We use invariably safe sets to lift safety verification from finite to infinite time horizons. In addition, our sets can be used to determine the existence of feasible evasive maneuvers and the criticality of scenarios by computing the time-to-react metric.

Absolute orientation estimation is the determination of the similarity transformation between two sets of corresponding 3D points, a task arising frequently in computer vision and robotics. We have recently proposed an absolute orientation algorithm based on the Fast Optimal Attitude Matrix (FOAM) algorithm from astronautics and demonstrated that it is more efficient computationally compared to widely-used approaches involving costly eigenand singular-value matrix decompositions. In this work, we compare our FOAM-based solution with several more algorithms derived from attitude estimation techniques and show that further computational savings are possible by employing an algorithm grounded on the Optimal Linear Attitude Estimator (OLAE) method.

Human-robot interaction research to date has investigated intent recognition and communication separately. In this paper, we explore the effects of integrating both the robot's ability to generate intentional motion and predict the human's motion in a collaborative physical task. We implemented an intent recognition system to recognize the human partner's hand motion intent and a motion planner system to enable the robot to communicate its intent by using legible and predictable motion. We tested this bi-directional intent system in a 2-way within-subjects user study. Results suggest that an integrated intent recognition and communication system may facilitate more collaborative behavior among team members.

This paper proposes an edge-based robust RGB-D visual odometry (VO) using 2-D edge divergence minimization. Our approach focuses on enabling the VO to operate in more general environments subject to low texture and changing brightness, by employing image edge regions and their image gradient vectors within the iterative closest points (ICP) framework. For more robust and stable ICP-based optimization, we propose a robust edge matching criterion with image gradient vectors. In addition, to reduce a bad effect of outlier residuals, we propose an improved edge registration problem of 2-D edge divergence minimization in the manner of an iterative re-weight least squares (IRLS) motion estimation. To accelerate the proposed approach, a pixel sub-sampling method is employed. We evaluate estimation performance of our method in changing brightness conditions and low-textured scenes. Our approach shows more robust motion estimation than state-of-the-art methods while maintaining comparable accuracy in challenging image sequences at real-time (25 Hz) operation.

In this paper, we propose novel edge and corner detection algorithms for unorganized point clouds. Our edge detection method evaluates symmetry in a local neighborhood and uses an adaptive density based threshold to differentiate 3D edge points. We extend this algorithm to propose a novel corner detector that clusters curvature vectors and uses their geometrical statistics to classify a point as corner. We perform rigorous evaluation of the algorithms on RGB-D semantic segmentation and 3D washer models from the ShapeNet dataset and report higher precision and recall scores. Finally, we also demonstrate how our edge and corner detectors can be used as a novel approach towards automatic weld seam detection for robotic welding. We propose to generate weld seams directly from a point cloud as opposed to using 3D models for offline planning of welding paths. For this application, we show a comparison between Harris 3D and our proposed approach on a panel workpiece.