IROS 2020 论文列表

Robot-Assisted systems for Minimally Invasive Surgery enhance the surgeon capability, however, direct control over both the surgical tools and the endoscope results in an increased workload that leads to longer operation times. This work investigates the introduction of SCAN (System for Camera Autonomous Navigation) to overcome this limitation. An experimental study involving 12 participants was carried out with the da Vinci Research Kit. Each user tested two novel camera control modalities, autonomous and semi-autonomous, as well as the current manual control of the camera, while carrying out a dry-lab task. Among the camera control modalities, the autonomous navigation achieved better objective performances and the highest user confidence. Moreover, the autonomous control (along with the semi-autonomous one) was able to optimize some metrics related to the robotic surgery workflow.

Predicting the future trajectory of surrounding vehicles in a randomly varying traffic level is one of the most challenging problems in developing an autonomous vehicle. Since there is no pre-defined number of interacting vehicles participated in, the prediction network has to be scalable with respect to the number of vehicles in order to guarantee consistent performance in terms of both accuracy and computational load. In this paper, the first fully scalable trajectory prediction network, SCALE-Net, is proposed that can ensure both high prediction performance while keeping the computational load low regardless of the number of surrounding vehicles. The SCALE-Net employs the Edge-enhanced Graph Convolutional Neural Network (EGCN) for the inter-vehicular interaction embedding network. Since the proposed EGCN is inherently scalable with respect to the graph node (an agent in this study), the model can be operated independently from the total number of vehicles considered. We evaluated the scalability of the SCALE-Net on the publically available NGSIM datasets by comparing variations on computation time and prediction accuracy per single driving scene with respect to the varying vehicle number. The experimental test shows that both computation time and prediction performance of the SCALE-Net consistently outperform those of previous models regardless of the level of traffic complexities.

Traditionally, controllers and state estimators in robotic systems are designed independently. Controllers are often designed assuming perfect state estimation. However, state estimation methods such as Visual Inertial Odometry (VIO) drift over time and can cause the system to misbehave. While state estimation error can be corrected with the aid of GPS or motion capture, these complementary sensors are not always available or reliable. Recent work has shown that this issue can be dealt with by synthesizing robust controllers using a data-driven characterization of the perception error, and can bound the system's response to state estimation error using a robustness constraint. We investigate the application of this robust perception-based approach to a quadrotor model using VIO for state estimation and demonstrate the benefits and drawbacks of using this technique in simulation and hardware. Additionally, to make tuning easier, we introduce a new cost function to use in the control synthesis which allows one to take an existing controller and "robustify" it. To the best of our knowledge, this is the first robust perception-based controller implemented in real hardware, as well as one utilizing a data-driven perception model. We believe this as an important step towards safe, robust robots that explicitly account for the inherent dependence between perception and control.

A crucial problem in human-robot collaboration is to achieve seamless coordination among the agents. Robots have to adapt to human behaviour, which is highly uncertain. In fact, humans can perform each task in many ways and with different speeds, occasional errors and short pauses. This paper offers a robust method to monitor the advancement of the current human activity in real-time in order to predict its duration. The algorithm learns online templates of new variants of the task and uses them as references for a Dynamic Time Warping-based algorithm. The proposed strategy has been tested within a realistic assembly task. Results show its ability to give accurate predictions also in case of peculiar variants, such as those associated with errors.

Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks. Object recognition using video data is more challenging than using still images due to blur, occlusions or rare object poses. Specific video detectors with high computational cost or standard image detectors together with a fast post-processing algorithm achieve the current state-of-the-art. This work introduces a novel post-processing pipeline that overcomes some of the limitations of previous post-processing methods by introducing a learning-based similarity evaluation between detections across frames. Our method improves the results of stat-of-the-art specific video detectors, specially regarding fast moving objects, and presents low resource requirements. And applied to efficient still image detectors, such as YOLO, provides comparable results to much more computationally intensive detectors.

Identifying new, moved or missing objects is an important capability for robot tasks such as surveillance or maintaining order in homes, offices and industrial settings. However, current approaches do not distinguish between novel objects or simple scene readjustments nor do they sufficiently deal with localization error and sensor noise. To overcome these limitations, we combine the strengths of global and local methods for efficient detection of novel objects in 3D reconstructions of indoor environments. Global structure, determined from 3D semantic information, is exploited to establish object candidates. These are then locally verified by comparing isolated geometry to a reference reconstruction provided by the task. We evaluate our approach on a novel dataset containing different types of rooms with 31 scenes and 260 annotated objects. Experiments show that our proposed approach significantly outperforms baseline methods.

Integrating robotic systems in architectural and construction processes is of core interest to increase the efficiency of the building industry. Automated planning for such systems enables design analysis tools and facilitates faster design iteration cycles for designers and engineers. However, generic task-and-motion planning (TAMP) for long-horizon construction processes is beyond the capabilities of current approaches. In this paper, we develop a multi-agent TAMP framework for long horizon problems such as constructing a full-scale building. To this end we extend the Logic-Geometric Programming framework by sampling-based motion planning, a limited horizon approach, and a task-specific structural stability optimization that allow an effective decomposition of the task. We show that our framework is capable of constructing a large pavilion built from several hundred geometrically unique building elements from start to end autonomously.

Robust and accurate estimation of liquid height lies as an essential part of pouring tasks for service robots. However, vision-based methods often fail in occluded conditions while audio-based methods cannot work well in a noisy environment. We instead propose a multimodal pouring network (MP-Net) that is able to robustly predict liquid height by conditioning on both audition and haptics input. MP-Net is trained on a self-collected multimodal pouring dataset. This dataset contains 300 robot pouring recordings with audio and force/torque measurements for three types of target containers. We also augment the audio data by inserting robot noise. We evaluated MP-Net on our collected dataset and a wide variety of robot experiments. Both network training results and robot experiments demonstrate that MP-Net is robust against noise and changes to the task and environment. Moreover, we further combine the predicted height and force data to estimate the shape of the target container.

In this paper, we address the issue of pedestrian tracking in crowd scenarios. People in close social relationships tend to act as a group which is a great challenge to individually discriminate and track pedestrians on a LiDAR system. In this paper, we integrally model groups of people and track them in a recursive framework based on Gaussian Mixture Model (GMM). The model is optimized by an extended Expectation-Maximization (EM) algorithm which can adaptively vary the number of mixture components over scans. Experimental results both qualitatively and quantitatively indicate the reliability and accuracy of our tracker in populated scenarios.

This work describes a monocular visual odometry framework, which exploits the best attributes of edge features for illumination-robust camera tracking, while at the same time ameliorating the performance degradation of edge mapping. In the front-end, an ICP-based edge registration provides robust motion estimation and coarse data association under lighting changes. In the back-end, a novel edge-guided data association pipeline searches for the best photometrically matched points along geometrically possible edges through template matching, so that the matches can be further refined in later bundle adjustment. The core of our proposed data association strategy lies in a point-to-edge geometric uncertainty analysis, which analytically derives (1) a probabilistic search length formula that significantly reduces the search space and (2) a geometric confidence metric for mapping degradation detection based on the predicted depth uncertainty. Moreover, a match confidence based patch size adaption strategy is integrated into our pipeline to reduce matching ambiguity. We present extensive analysis and evaluation of our proposed system on synthetic and real- world benchmark datasets under the influence of illumination changes and large camera motions, where our proposed system outperforms current state-of-art algorithms.

Robust particle manipulation is a challenging but essential technique for single-cell analysis and processing of microfluidic devices. This paper proposes a micro-particle manipulation system with a microfluidic channel network. We built gravity-induced pressure actuators, which can generate high-resolution output pressure with a wide range so that the multiple particles can be delivered from the inlet of the chip. In this paper, we studied how to model the proposed multi-input-single-output system and sources of disturbances, and designed a robust controller using disturbance observer technique. The performance of the proposed system was verified through experiments.

Intuitive human robot interfaces like speech or gesture recognition are essential for gaining acceptance for robots in daily life. However, such interaction requires that the robot detects the human's intention to interact, tracks his position and keeps its sensor systems in an optimal configuration. Audio is a suitable modality for such task as it allows for detecting a speaker in arbitrary positions around the robot. In this paper, we present a novel approach for localization of sound sources by analyzing the frequency spectrum of the received signal and applying a motion model to the estimation process. We use an improved version of the Generalized Singular Value Decomposition (GSVD) based MUltiple SIgnal Classification (MUSIC) algorithm as a direction of arrival (DoA) estimator. Further, we introduce a motion model to enable robust localization in reverberant and echoic environments.We evaluate the system under real conditions in an experimental setup. Our experiments show that our approach outperforms current state-of-the-art algorithm and demonstrate the robustness against the previously mentioned disruptive factors.

Electric motors have been widely used as the actuators of robot and automation systems. This paper aims at achieving the high-precision position control of motor drive systems. For this purpose, a robust control scheme is presented by combining the internal model principle, the sliding mode technique and the extended state observer (ESO). The PID-type controller is firstly designed by using the internal model control (IMC) rules. Since the analysis of the IMC system is performed via a sliding surface, a robust sliding mode control (SMC) law is then synthesized to enhance the control ability of the system to uncertainties. However, this robust solution should make a trade-off between the chattering attenuation and the control accuracy. To handle this drawback, a linear ESO is employed to compensate the modeling errors for a higher control accuracy. The stability analysis is provided via a Lyapunov-based method, and the superiority of the proposed approach was validated by comparative experiments on a motor drive platform.

Despite plenty of motion planning strategies have been proposed for bipedal locomotion, enhancing the walking robustness in real-world environments is still an open question. This paper focuses on robust body and leg trajectories synthesis through integrating constrained optimization with imitation learning. Specifically, we first propose a Quadratically Constrained Quadratic Programming (QCQP) algorithm to make use of the ankle strategy and stepping strategy. Based on the Linear Inverted Pendulum (LIP) model, body motion can be determined by the modulated Center of Pressure (CoP) position and step parameters (including step location and step duration). After that, we exploit an imitation learning approach Kernelized Movement Primitives (KMP) to plan robot leg motions, which allows for adapting the learned motion patterns to new situations (e.g., passing through various desired points) in a straightforward manner. Several LIP simulations and whole-body dynamic simulations demonstrate that higher walking robustness can be achieved using our framework.

Most current bipedal robots were modeled with an assumption that there is no slip between the stance foot and ground. This paper relaxes that assumption and undertakes a comprehensive study of a compass gait biped with foot slipping. It is found that slips are most likely to happen near impact for a broad range of gaits. Among these gaits, ones with a backward swing foot velocity relative to the ground just before touch down generally require less friction to maintain stable walking than ones with a forward relative foot velocity. Moreover, a larger percentage of gaits with the "swinging backward" foot can tolerate some slipping without falling than those with a swinging forward foot at touch down. Thus, a gait with the swing-backward foot just before touch down should be more robust in the sense of preventing slipping and falling. It is further shown that only one parameter in gait design determines the swing-backward feature, which can help design robust gaits. Models with varying physical parameters such as mass, leg length, and position of center of mass (CoM), are also studied to validate the generality of the results.

Robotic systems are increasingly required not only to generate precise motions to complete their tasks but also to handle the interactions with the environment or human. Significantly, soft interaction brings great challenges on the force control due to the nonlinear, viscoelastic and inhomogeneous properties of the soft environment. In this paper, a robust impedance control scheme utilizing integral backstepping technology and integral terminal sliding mode control is proposed to achieve force tracking for an ultrasonic motor-actuated end-effector in a soft environment. In particular, the steady-state performance of the target impedance while in contact with soft environment is derived and analyzed with the nonlinear Hunt-Crossley model. Finally, the dynamic force tracking performance of the proposed control scheme is verified via several experiments.

The problem of tracking self-motion as well as motion of objects in the scene using information from a camera is known as multi-body visual odometry and is a challenging task. This paper proposes a robust solution to achieve accurate estimation and consistent track-ability for dynamic multi-body visual odometry. A compact and effective framework is proposed leveraging recent advances in semantic instance-level segmentation and accurate optical flow estimation. A novel formulation, jointly optimizing SE(3) motion and optical flow is introduced that improves the quality of the tracked points and the motion estimation accuracy. The proposed approach is evaluated on the virtual KITTI Dataset and tested on the real KITTI Dataset, demonstrating its applicability to autonomous driving applications. For the benefit of the community, we make the source code public†.

In this paper, we propose a dynamic state estimation framework for lateral control of a heavy tractor-trailers system using only mass-produced low-cost sensors. This issue is challenging since the lateral velocity of the lead tractor is difficult to measure directly. The performance of existing dynamic model-based estimation methods will also be degraded, as different trailers and payloads cause the tractor model parameters to change. We address this issue by incorporating a kinematic estimator into a dynamic model-based estimation scheme. Accurate and reliable tire cornering stiffness and dynamics-informed lateral velocity of the lead tractor can be output in real-time by using our method. The stability and robustness of the proposed method are theoretically proved. The feasibility of our method is verified by full-scale experiments. It is also verified that the estimated model parameters and lateral states do improve the control performance by integrating the estimator into a lateral control system.

Control of wire-borne underactuated brachiating robots requires a robust feedback control design that can deal with dynamic uncertainties, actuator constraints and unmeasurable states. In this paper, we develop a robust feedback control for brachiating on flexible cables, building on previous work on optimal trajectory generation and time-varying LQR controller design. We propose a novel simplified model for approximation of the flexible cable dynamics, which enables inclusion of parametric model uncertainties in the system. We then use semidefinite programming (SDP) and sum-of-squares (SOS) optimization to synthesize a time-varying feedback control with formal robustness guarantees to account for model uncertainties and unmeasurable states in the system. Through simulation, hardware experiments and comparison with a time-varying LQR controller, it is shown that the proposed robust controller results in relatively large robust backward reachable sets and is able to reliably track a pre-generated optimal trajectory and achieve the desired brachiating motion in the presence of parametric model uncertainties, actuator limits, and unobservable states.