ICRA 2020 论文列表

In the present paper, we first adopt explicit force control from general robotics and embed it into teleoperation systems to enhance the transparency by reducing the effect of the perceived inertia to the human operator and simultaneously improve contact perception. To ensure stability of the proposed teleoperation system considering time-delays, we propose a sequential design procedure based on time domain passivity approach. Experimental results of master-slave teleoperation system, based on KUKA light-weight-robots, for different values of delays are presented. Comparative analysis is conducted considering two existing approaches, namely 2-channel and 4-channel architecture based bilateral controllers, and its results clearly indicate significant improvement in force transparency owing to the proposed method. The proposed system is finally validated considering a real industrial assembly scenario.

Visual-inertial SLAM is essential for robot navigation in GPS-denied environments, e.g. indoor, underground. Conventionally, the performance of visual-inertial SLAM is evaluated with open-loop analysis, with a focus on the drift level of SLAM systems. In this paper, we raise the question on the importance of visual estimation latency in closed-loop navigation tasks, such as accurate trajectory tracking. To understand the impact of both drift and latency on visualinertial SLAM systems, a closed-loop benchmarking simulation is conducted, where a robot is commanded to follow a desired trajectory using the feedback from visual-inertial estimation. By extensively evaluating the trajectory tracking performance of representative state-of-the-art visual-inertial SLAM systems, we reveal the importance of latency reduction in visual estimation module of these systems. The findings suggest directions of future improvements for visual-inertial SLAM.

The Dynamic Visual Sensor is considered to be a next-generation vision sensor. Since event-based vision is in its early stage of development, a small number of datasets has been created during the last decade. Dataset creation is motivated by the need for real data from one or many sensors. Temporal accuracy of data in such datasets is crucially important since the events have high temporal resolution measured in microseconds and, during an algorithm evaluation task, such type of visual data is usually fused with data from other types of sensors. The main aim of our research is to achieve the most accurate possible time synchronization between an event camera, LIDAR, and ambient environment sensors during a session of data acquisition. All the mentioned sensors as well as a stereo and a monocular camera were installed on a mobile robotic platform. In this work, a time synchronization architecture and algorithm are proposed for time synchronization with an implementation example on a PIC32 microcontroller. The overall time synchronization approach is scalable for other sensors where there is a need for accurate time synchronization between many nodes. The evaluation results of the proposed solution are reported and discussed in the paper.

Transparent objects are a common part of everyday life, yet they possess unique visual properties that make them incredibly difficult for standard 3D sensors to produce accurate depth estimates for. In many cases, they often appear as noisy or distorted approximations of the surfaces that lie behind them. To address these challenges, we present ClearGrasp - a deep learning approach for estimating accurate 3D geometry of transparent objects from a single RGB-D image for robotic manipulation. Given a single RGB-D image of transparent objects, ClearGrasp uses deep convolutional networks to infer surface normals, masks of transparent surfaces, and occlusion boundaries. It then uses these outputs to refine the initial depth estimates for all transparent surfaces in the scene. To train and test ClearGrasp, we construct a large-scale synthetic dataset of over 50,000 RGB-D images, as well as a real-world test benchmark with 286 RGB-D images of transparent objects and their ground truth geometries. The experiments demonstrate that ClearGrasp is substantially better than monocular depth estimation baselines and is capable of generalizing to real-world images and novel objects. We also demonstrate that ClearGrasp can be applied out-of-the-box to improve grasping algorithms' performance on transparent objects. Code, data, and benchmarks will be released. Supplementary materials: https://sites.google.com/view/cleargrasp.

Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end manner, these algorithms require large amounts of experience to learn navigation policies from high-dimensional data, which is generally impractical for real robots due to sample complexity. In this paper, we address these problems with two main contributions. We first leverage place recognition and deep learning techniques combined with goal destination feedback to generate compact, bimodal image representations that can then be used to effectively learn control policies from a small amount of experience. Second, we present an interactive framework, CityLearn, that enables for the first time training and deployment of navigation algorithms across city-sized, realistic environments with extreme visual appearance changes. CityLearn features more than 10 benchmark datasets, often used in visual place recognition and autonomous driving research, including over 100 recorded traversals across 60 cities around the world. We evaluate our approach on two CityLearn environments, training our navigation policy on a single traversal per dataset. Results show our method can be over 2 orders of magnitude faster than when using raw images, and can also generalize across extreme visual changes including day to night and summer to winter transitions.

Actuators are essential devices that exert force and do work. The contraction of an actuator (how much it can shorten) is an important property that strongly influences its applications, especially in engineering and robotics. While high contractions have been achieved by thermally- or fluidically-driven technologies, electrically-driven actuators typically cannot contract by more than 50%. Recently developed electro-ribbon actuators are simple, low cost, scalable electroactive devices powered by dielectrophoretic liquid zipping (DLZ) that exhibit high efficiency (~70%), high power equivalent to mammalian muscle (~100 W/kg), contractions exceeding 99%. We characterise the electro-ribbon actuator and explore contraction variation with voltage and load. We describe the unique self-locking behaviour of the electro-ribbon actuator which could allow for low-power-consumption solenoids and valves. Finally, we show the interdependence of constituent material properties and the important role that material choice plays in maximising performance.

A variety of optimization problems takes the form of a minimum norm optimization. In this paper, we study the change of optimal values between two incrementally constructed least norm optimization problems, with new measurements included in the second one. We prove an exact equation to calculate the change of optimal values in the linear least norm optimization problem. With the result in this paper, the change of the optimal values can be pre-calculated as a metric to guide online decision makings, without solving the second optimization problem as long the solution and covariance of the first optimization problem are available. The result can be extended to linear least distance optimization problems, and nonlinear least distance optimization with (nonlinear) equality constraints through linearizations. This derivation in this paper provides a theoretically sound explanation to the empirical observations shown in [1]. As an additional contribution, we propose another optimization problem, i.e. aligning two trajectories at given poses, to further demonstrate how to use the metric. The accuracy of the metric is validated with numerical examples, which is quite satisfactory in general (see the experiments in [1] as well), unless in some extremely adverse scenarios. Last but not least, calculating the optimal value by the proposed metric is at least one magnitude faster than solving the corresponding optimization problems directly.

We present a novel algorithm for simultaneous task assignment and path planning on a graph (or roadmap) with stochastic edge costs. In this problem, the initially unassigned robots and tasks are located at known positions in a roadmap. We want to assign a unique task to each robot and compute a path for the robot to go to its assigned task location. Given the mean and variance of travel cost of each edge, our goal is to develop algorithms that, with high probability, the total path cost of the robot team is below a minimum value in any realization of the stochastic travel costs. We formulate the problem as a chance-constrained simultaneous task assignment and path planning problem (CC-STAP). We prove that the optimal solution of CC-STAP can be obtained by solving a sequence of deterministic simultaneous task assignment and path planning problems in which the travel cost is a linear combination of mean and variance of the edge cost. We show that the deterministic problem can be solved in two steps. In the first step, robots compute the shortest paths to the task locations and in the second step, the robots solve a linear assignment problem with the costs obtained in the first step. We also propose a distributed algorithm that solves CC-STAP near-optimally. We present simulation results on randomly generated networks and data to demonstrate that our algorithm is scalable with the number of robots (or tasks) and the size of the network.

An unstable grasp pose can lead to slip, thus an unstable grasp pose can be predicted by slip detection. A regrasp is required afterwards to correct the grasp pose in order to finish the task. In this work, we propose a novel regrasp planner with multi-sensor modules to plan grasp adjustments with the feedback from a slip detector. Then a regrasp planner is trained to estimate the location of center of mass, which helps robots find an optimal grasp pose. The dataset in this work consists of 1 025 slip experiments and 1 347 regrasps collected by one pair of tactile sensors, an RGB-D camera and one Franka Emika robot arm equipped with joint force/torque sensors. We show that our algorithm can successfully detect and classify the slip for 5 unknown test objects with an accuracy of 76.88% and a regrasp planner increases the grasp success rate by 31.0% compared to the state-of-the-art vision-based grasping algorithm.

Socially assistive robots have the potential to improve group dynamics when interacting with groups of people in social settings. This work contributes to the understanding of those dynamics through a user study of trust dynamics in the novel context of a robot mediated support group. For this study, a novel framework for robot mediation of a support group was developed and validated. To evaluate interpersonal trust in the multi-party setting, a dyadic trust scale was implemented and found to be uni-factorial, validating it as an appropriate measure of general trust. The results of this study demonstrate a significant increase in average interpersonal trust after the group interaction session, and qualitative post-session interview data report that participants found the interaction helpful and successfully supported and learned from one other. The results of the study validate that a robot-mediated support group can improve trust among strangers and allow them to share and receive support for their academic stress.

We present an approach for estimating the pose of an external camera with respect to a robot using a single RGB image of the robot. The image is processed by a deep neural network to detect 2D projections of keypoints (such as joints) associated with the robot. The network is trained entirely on simulated data using domain randomization to bridge the reality gap. Perspective-n-point (PnP) is then used to recover the camera extrinsics, assuming that the camera intrinsics and joint configuration of the robot manipulator are known. Unlike classic hand-eye calibration systems, our method does not require an off-line calibration step. Rather, it is capable of computing the camera extrinsics from a single frame, thus opening the possibility of on-line calibration. We show experimental results for three different robots and camera sensors, demonstrating that our approach is able to achieve accuracy with a single frame that is comparable to that of classic off-line hand-eye calibration using multiple frames. With additional frames from a static pose, accuracy improves even further. Code, datasets, and pretrained models for three widely-used robot manipulators are made available.

Tracking the pose of a camera is at the core of visual localization methods used in many applications. As the observations of a camera are inherently affected by lighting, it has always been a challenge for these methods to cope with varying lighting conditions. Thus far, this issue has mainly been approached with the intent to increase robustness by choosing lighting invariant map representations. In contrast, our work aims at explicitly exploiting lighting effects for camera tracking. To achieve this, we propose a lighting adaptable map representation for indoor environments that allows real-time rendering of the scene illuminated by an arbitrary subset of the lamps contained in the model. Our method for estimating the light setting from the current camera observation enables us to adapt the model according to the lighting conditions present in the scene. As a result, lighting effects like cast shadows do no longer act as disturbances that demand robustness but rather as beneficial features when matching observations against the map. We leverage these capabilities in a direct dense camera tracking approach and demonstrate its performance in realworld experiments in scenes with varying lighting conditions.

Tactile sensors based on electrical resistance tomography (ERT) have shown many advantages for implementing a soft and scalable whole-body robotic skin; however, calibration is challenging because pressure reconstruction is an ill-posed inverse problem. This paper introduces a method for calibrating soft ERT-based tactile sensors using sim-to-real transfer learning with a finite element multiphysics model. The model is composed of three simple models that together map contact pressure distributions to voltage measurements. We optimized the model parameters to reduce the gap between the simulation and reality. As a preliminary study, we discretized the sensing points into a 6 by 6 grid and synthesized single- and two-point contact datasets from the multiphysics model. We obtained another single-point dataset using the real sensor with the same contact location and force used in the simulation. Our new deep neural network architecture uses a de-noising network to capture the simulation-to-real gap and a reconstruction network to estimate contact force from voltage measurements. The proposed approach showed 82% hit rate for localization and 0.51 N of force estimation error performance in singlecontact tests and 78.5% hit rate for localization and 5.0 N of force estimation error in two-point contact tests. We believe this new calibration method has the possibility to improve the sensing performance of ERT-based tactile sensors.

It is difficult for both cameras and depth sensors to obtain reliable information in hazy scenes. Therefore, image dehazing is still one of the most challenging problems to solve in computer vision and robotics. With the development of convolutional neural networks (CNNs), lots of dehazing and depth estimation algorithms using CNNs have emerged. However, very few of those try to solve these two problems at the same time. Focusing on the fact that traditional haze modeling contains depth information in its formula, we propose a CNN-based simultaneous dehazing and depth estimation network. Our network aims to estimate both a dehazed image and a fully scaled depth map from a single hazy RGB input with end-to-end training. The network contains a single dense encoder and four separate decoders; each of them shares the encoded image representation while performing individual tasks. We suggest a novel depth-transmission consistency loss in the training scheme to fully utilize the correlation between the depth information and transmission map. To demonstrate the robustness and effectiveness of our algorithm, we performed various ablation studies and compared our results to those of state-of-the-art algorithms in dehazing and single image depth estimation, both qualitatively and quantitatively. Furthermore, we show the generality of our network by applying it to some real-world examples.

Naturalistic driving trajectory generation is crucial for the development of autonomous driving algorithms. However, most of the data is collected in collision-free scenarios leading to the sparsity of the safety-critical cases. When considering safety, testing algorithms in near-miss scenarios that rarely show up in off-the-shelf datasets and are costly to accumulate is a vital part of the evaluation. As a remedy, we propose a safety-critical data synthesizing framework based on variational Bayesian methods and term it as Conditional Multiple Trajectory Synthesizer (CMTS). We extend a generative model to connect safe and collision driving data by representing their distribution in the latent space and use conditional probability to adapt to different maps. Sampling from the mixed distribution enables us to synthesize the safety-critical data not shown in the safe or collision datasets. Experimental results demonstrate that the generated dataset covers many different realistic scenarios, especially the near-misses. We conclude that the use of data generated by CMTS can improve the accuracy of trajectory predictions and autonomous vehicle safety.

This paper presents a novel Cable Climbing Robot CCRobot-III, which is the third version designed for bridge cable inspection tasks, aiming at surpassing previous versions in terms of climbing speed and payload capacity. Benefiting from Split-type Wire-driven design, CCRobot-III can climb along a 90-110mm diameter bridge cable in inchworm-like gait at a speed of up to 12m/min, and carrying more than 40kg payload at the same time. CCRobot-III consists of a climbing precursor and a main-body frame. The two parts are connected and driven by steel wires. The climbing precursor, acting as a mobile anchor, moves quickly on a bridge cable. The mainbody frame, acting as a mobile winch, carries payload and pulls itself to a certain position with steel wires. Both parts have one or two pairs of palm-based gripper, which is the key component for providing strong adhesion to support the robot climbing. Experimental results have shown that CCRobotIII possesses outstanding climbing performance, high payload capacity, and good adaptability to complex conditions of cable surface. Moreover, it has potential engineering applications on the cable-stayed bridge for fieldwork.

Instance grasping is a challenging robotic grasping task when a robot aims to grasp a specified target object in cluttered scenes. In this paper, we propose a novel end-to-end instance grasping method using only monocular workspace and query images, where the workspace image includes several objects and the query image only contains the target object. To effectively extract discriminative features and facilitate the training process, a learning-based method, referred to as Constraint Co-Attention Network (CCAN), is proposed which consists of a constraint co-attention module and a grasp affordance predictor. An effective co-attention module is presented to construct the features of a workspace image from the extracted features of the query image. By introducing soft constraints into the co-attention module, it highlights the target object's features while trivializes other objects' features in the workspace image. Using the features extracted from the co-attention module, the cascaded grasp affordance interpreter network only predicts the grasp configuration for the target object. The training of the CCAN is totally based on simulated self-supervision. Extensive qualitative and quantitative experiments show the effectiveness of our method both in simulated and real-world environments even for totally unseen objects.

Using multiple robots for exploring and mapping environments can provide improved robustness and performance, but it can be difficult to implement. In particular, limited communication bandwidth is a considerable constraint when a robot needs to determine if it has visited a location that was previously explored by another robot, as it requires for robots to share descriptions of places they have visited. One way to compress this description is to use constellations, groups of 3D points that correspond to the estimate of a set of relative object positions. Constellations maintain the same pattern from different viewpoints and can be robust to illumination changes or dynamic elements. We present a method to extract from these constellations compact spatial and semantic descriptors of the objects in a scene. We use this representation in a 2step decentralized loop closure verification: first, we distribute the compact semantic descriptors to determine which other robots might have seen scenes with similar objects; then we query matching robots with the full constellation to validate the match using geometric information. The proposed method requires less memory, is more interpretable than global image descriptors, and could be useful for other tasks and interactions with the environment. We validate our system's performance on a TUM RGB-D SLAM sequence and show its benefits in terms of bandwidth requirements.

This work presents a novel design concept that achieves multi-legged locomotion using a three-dimensional cam system. A computational framework has been developed to analyze and dimension this cam apparatus, that can perform arbitrary end effector motions within its design constraints. The mechanism enables continuous gait transition and inherent force compliance. With only two motors, any trajectory of a continuous set of gaits can be followed. One motor is used to actuate the system and a second one to morph its movement. To illustrate a possible application of this system, a working prototype of a bipedal robot is developed and validated in hardware. It showcases a smooth velocity change by transitioning through different gaits from standing still to walking fast at 124mm/s within 2.0s, while following the given end effector trajectory with an error of only 2.47mm.