IROS 2020 论文列表

This paper deals with continuous tension validation for Cable-Driven Parallel Robots (CDPRs). The proposed method aims at determining whether or not a quasi-static path is feasible regarding cable tension limits. The available wrench set (AWS) is the set of wrenches that can be generated with cable tensions within given minimum and maximum limits. A pose of the robot is considered valid regarding the tensions if and only if the wrench induced by the platform weight is inside the AWS. The hyperplane shifting method gives a geometric representation of the AWS as the intersection of half-spaces. For each facet-defining hyperplane of the AWS, we define a value which is positive when the pose is valid, i.e. when the corresponding wrench lies on the proper side of the hyperplane. Using this value and an upper bound on its time derivative along the path, the half-length of a valid time interval is obtained. Intervals are repeatedly validated for each hyperplane until either the whole path is validated or a non-valid pose is found. The presented method is integrated within the open-source software Humanoid Path Planner (HPP) and implementation results using the configuration of the CDPR CoGiRo are presented.

In the next few years, the amount and variety of context-aware robotic manipulator applications is expected to increase significantly, especially in household environments. In such spaces, thanks to programming by demonstration, non-expert people will be able to teach robots how to perform specific tasks, for which the adaptation to the environment is imperative, for the sake of effectiveness and users safety. These robot motion learning procedures allow the encoding of such tasks by means of parameterized trajectory generators, usually a Movement Primitive (MP) conditioned on contextual variables. However, naively sampled solutions from these MPs are generally suboptimal/inefficient, according to a given reward function. Hence, Policy Search (PS) algorithms leverage the information of the experienced rewards to improve the robot performance over executions, even for new context configurations. Given the complexity of the aforementioned tasks, PS methods face the challenge of exploring in high-dimensional parameter search spaces. In this work, a solution combining Bayesian Optimization, a data-efficient PS algorithm, with covariate Gaussian Process Latent Variable Models, a recent Dimensionality Reduction technique, is presented. It enables reducing dimensionality and exploiting prior demonstrations to converge in few iterations, while also being compliant with context requirements. Thus, contextual variables are considered in the latent search space, from which a surrogate model for the reward function is built. Then, samples are generated in a low-dimensional latent space, and mapped to a context-dependent trajectory. This allows us to drastically reduce the search space with the covariate GPLVM, e.g. from 105 to 2 parameters, plus a few contextual features. Experimentation in two different scenarios proves the data-efficiency and the power of dimensionality reduction of our approach.

Localizing contacts and collisions is an important aspect of failure detection and recovery for robots and can aid perception and exploration of the environment. Contrary to state-of-the-art methods that rely on forces and torques measured on the robot, this paper proposes a kinematic method for proprioceptive contact localization on compliant robots using velocity measurements. The method is validated on two planar robots, the quadrupedal Minitaur and the two-fingered Direct Drive (DD) Hand which are compliant due to inherent transparency from direct drive actuation. Comparisons to other state-of-the-art proprioceptive methods are shown in simulation. Preliminary results on further extensions to complex geometry (through numerical methods) and spatial robots (with a particle filter) are discussed.

A floating base system is inevitably to contact the environment while it is moving. This paper explores the contact force estimation and regulation algorithm for a position-controlled floating base system without joint torque information. First, the joint space dynamic model of the system is presented and transformed into the contact space. Then, the inverse dynamics method is employed to estimate the contact forces. After that, a proportional-integral (PI) regulator is designed to drive the contact forces to track the desired values. Finally, the feasibility of this algorithm is demonstrated on a simulated bipedal platform.

In this paper, we have constructed actively perfusable multiple hepatic lobule-like vascular networks in a 3D cellular structure by using magnetic tweezers. Without well-organized channel networks, cells in a large 3D tissue cannot receive nutrients and oxygen from the channel, and therefore, the cells will be dead after few days. To construct well-organized channel networks, we fabricated a hepatic lobule like vascular networks by using magnetic fields in our previous works. However, the size of the hepatic lobule like vascular network was more than five times larger than real hepatic tissue. To improve the previous research, we have proposed several things. First, we have constructed the vascular network having similar size of the real thing in this step. Second, we have cultured the constructed structure for a long-time (more than two weeks) to verify the biocompatible condition. Third, we assemble the constructed hepatic tissues to make a large size of organ, liver. Finally, an actively perfusable system have been adopted to implement a bioreactor system by adding micro pump.

Sensor fusion systems merging (multiple) delayed sensor signals through a statistical approach are challenging setups, particularly for resource constrained platforms. For statistical consistency, one would be required to keep an appropriate history, apply the correcting signal at the given time stamp in the past, and re-apply all information received until the present time. This re-calculation becomes impractical (the bottleneck being the re-propagation of the covariance matrices for estimator consistency) for platforms with multiple sensors/states and low compute power.This work presents a novel approach for consistent covariance pre-integration allowing delayed sensor signals to be incorporated in a statistically consistent fashion with very low complexity. We leverage recent insights in Invariant Extended Kalman Filters (IEKF) and their log-linear, state independent error propagation together with insights from the scattering theory to mimic the re-calculation process as a medium through which we can propagate waves (covariance information in this case) in single operation steps. We support our findings in simulation and with real data.

Motion planning for robots of high degrees-of-freedom (DOFs) is an important problem in robotics with sampling-based methods in configuration space \mathcal{C}\mathcal{C} as one popular solution. Recently, machine learning methods have been introduced into sampling-based motion planning methods, which train a classifier to distinguish collision free subspace from in-collision subspace in \mathcal{C}\mathcal{C}. In this paper, we propose a novel configuration space decomposition method and show two nice properties resulted from this decomposition. Using these two properties, we build a composite classifier that works compatibly with previous machine learning methods by using them as the elementary classifiers. Experimental results are presented, showing that our composite classifier outperforms state-of-the-art single-classifier methods by a large margin. A real application of motion planning in a multi-robot system in plant phenotyping using three UR5 robotic arms is also presented.

Accurate and reliable 3D object detection is vital to safe autonomous driving. Despite recent developments, the performance gap between stereo-based methods and LiDAR-based methods is still considerable. Accurate depth estimation is crucial to the performance of stereo-based 3D object detection methods, particularly for those pixels associated with objects in the foreground. Moreover, stereo-based methods suffer from high variance in the depth estimation accuracy, which is often not considered in the object detection pipeline. To tackle these two issues, we propose CG-Stereo, a confidence-guided stereo 3D object detection pipeline that uses separate decoders for foreground and background pixels during depth estimation, and leverages the confidence estimation from the depth estimation network as a soft attention mechanism in the 3D object detector. Our approach outperforms all state-of-the-art stereo-based 3D detectors on the KITTI benchmark.

We investigate the task and motion planning problem of clearing clutter from a workspace with limited ingress/egress access for multiple robots. We call the problem multi-robot clutter removal (MRCR). Targeting practical applications where motion planning is non-trivial but is not a bottle-neck, we focus on finding high-quality solutions for feasible MRCR instances, which depends on the ability to efficiently compute high-quality object removal sequences. Despite the challenging multi-robot setting, our proposed search algorithms based on A*, dynamic programming, and best-first heuristics all produce solutions for tens of objects that significantly outperform single robot solutions. Realistic simulations with multiple Kuka youBots further confirms the effectiveness of our algorithmic solutions. In contrast, we also show that deciding the optimal object removal sequence for MRCR is computationally intractable.

For accomplishing a variety of missions in challenging environments, the capability of navigating with full autonomy while avoiding unexpected obstacles is the most crucial requirement for UAVs in real applications. In this paper, we proposed such a computationally efficient obstacle avoidance trajectory planner that can be used in unknown cluttered environments. Because of the narrow view field of single depth camera on a UAV, the information of obstacles around is quite limited thus the shortest entire path is difficult to achieve. Therefore we focus on the time cost of the trajectory planner and safety rather than other factors. This planner is mainly composed of a point cloud processor, a waypoint publisher with Heuristic Angular Search(HAS) method and a motion planner with minimum acceleration optimization. Furthermore, we propose several techniques to enhance safety by making the possibility of finding a feasible trajectory as large as possible. The proposed approach is implemented to run onboard in real-time and is tested extensively in simulation and the average control output calculating time of iteration steps is less than 18 ms.

We consider the design of under-actuated articulated mechanism that are able to maintain stable static balance. Our method augments an user-provided design with counter-weights whose mass and attachment locations are automatically computed. The optimized counterweights adjust the center of gravity such that, for bounded external perturbations, the mechanism returns to its original configuration. Using our sketch-based system, we present several examples illustrating a wide range of user-provided designs can be successfully converted into statically-balanced mechanisms. We further validate our results with a set of physical prototypes.

Aerial robotic manipulation is an emergent trend that poses several challenges. To overcome some of these, the DLR cable-Suspended Aerial Manipulator (SAM) has been envisioned. SAM is composed of a fully actuated multi-rotor anchored to a main carrier through a cable and a KUKA LWR attached below the multi-rotor. This work presents a control method to allow SAM, which is a holonomically constrained system, to perform such interaction tasks using a hierarchical control framework. Within this framework, compliance control of the manipulator end-effector is considered to have the highest priority. The second priority is the control of the oscillations induced by, for example, the motion of the arm or physical contact with the environment. A third priority task is related to the internal motion of the manipulator. The proposed approach is validated through simulations and experiments.

This paper develops a coverage-centric adaptive path planner to visually survey a planar environment. This is achieved by modifying an existing path planning architecture to use a novel coverage estimation approach called convolved coverage estimation (CCE). The planner maximizes the probability of terrain coverage and exploits terrain features for loop closure to keep path uncertainty in check. The developed algorithm considers multi-dimensional uncertainty, operates in real-time, and does not require external correction methods like GPS. These characteristics are validated in high-fidelity simulation and flight tests on an unmanned aerial vehicle (UAV).

This paper introduces the competitive coverage problem, a new variant of the robotic coverage problem in which a robot R competes with another robot O in order to be the first to cover an area. In the variant discussed in this paper, the asymmetric competitive coverage, O is unaware of the existence of R, which attempts to take that fact into consideration in order to succeed in being the first to cover as many parts of the environment as possible. We consider different information models of R that define how much it knows about the location of O and its planned coverage path. We present an optimal algorithm for R in the full-information case, and show that unless R has information about O's initial location, it is as if it has no information at all. Lastly, we describe a correlation between the time it takes R to reach O's initial location and the coverage paths quality, and present a heuristic algorithm for the case in which R has information only about O's initial location, showing its superiority compared to other coverage algorithms in rigorous simulation experiments.

In-space assembly (ISA) is the next step to building larger and more permanent structures in orbit. The use of a robotic in-space assembler saves on costly and potentially risky EVAs. Determining the best robot for ISA is difficult as it will depend on the structure being assembled. A comparison between two categories of robots is presented: a stationary robot and robot which crawls along the truss. The estimated mass, energy, and time are presented for each system as it, in simulation, builds a desired truss system. There are trade-offs to every robot design and understanding those trade-offs is essential to building a system that is not only efficient but also cost-effective.

This paper presents a new open-source dataset with ground truth position in a simulated colon environment to promote development of real-time feedback systems for physicians performing colonoscopies. Four systems (DSO, LSD-SLAM, SfMLearner, ORB-SLAM2) are tested on this dataset and their failures are analyzed. A data collection platform was fabricated and used to take the dataset in a colonoscopy training simulator that was affixed to a flat surface. The noise in the ground truth positional data induced from the metal in the data collection platform was then characterized and corrected. The Absolute Trajectory RMSE Error (ATE) and Relative Error (RE) metrics were performed on each of the sequences in the dataset for each of the Simultaneous Localization And Mapping (SLAM) systems. While these systems all had good performance in idealized conditions, more realistic conditions in the harder sequences caused them to produce poor results or fail completely. These failures will be a hindrance to physicians in a real-world scenario, so future systems made for this environment must be more robust to the difficulties found in the colon, even at the expense of trajectory accuracy. The authors believe that this is the first open-source dataset with groundtruth data displaying a simulated in vivo environment with active deformation, and that this is the first step toward achieving useful SLAM within the colon. The dataset is available at www.colorado.edu/lab/amtl/datasets.

Current trends in industrial automation favor agile systems that allow adaptation to rapidly changing task requirements and facilitate customized production in smaller batches. This work presents a flexible manufacturing system relying on compliance control, CAD based localization, and a multi-modal gripper to enable fast and efficient task programming for assembly operations. CAD file processing is employed to extract component pose data from 3D assembly models, while the system's active compliance compensates for errors in calibration or positioning. To minimize retooling delays, a novel gripper design incorporating both a parallel jaw element and a rotating module is proposed. The developed system placed first in the manufacturing track of the Robotic Grasping and Manipulation Competition of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2019, experimentally validating its efficiency.

Accurately tracking dynamic targets relies on robots accounting for uncertainties in their own states to share information and maintain safety. The problem becomes even more challenging when there is an unknown and time-varying number of targets in the environment. In this paper we address this problem by introducing four new distributed algorithms that allow large teams of robots to: i) run the prediction and ii) update steps of a distributed recursive Bayesian multi- target tracker, iii) determine the set of local neighbors that must exchange data, and iv) exchange data in a consistent manner. All of these algorithms account for a bounded level of localization uncertainty in the robots by leveraging our recent introduction of the convex uncertainty Voronoi (CUV) diagram, which extends the traditional Voronoi diagram to account for localization uncertainty. The CUV diagram introduces a tessellation over the environment, which we use in this work both to distribute the multi-target tracker and to make control decisions about where to search next. We examine the efficacy of our method via a series of simulations and compare them to our previous work which assumed perfect localization.

With the aim of contributing to the development of a robotic attendant system, this study proposes the concept of assessing the risk of collision using awareness estimation. The proposed approach enables an attendant robot to assess a person's risk of colliding with an obstacle by estimating whether he/she is aware of it based on behavior, and to take the requisite preventative action. To implement the proposed concept, we design a model that can simultaneously estimate a person's awareness of obstacles and predict his/her trajectory based on a convolutional neural network. When trained on a dataset of collision-related behaviors generated from people trajectory datasets, the model can detect objects of which the person is not aware and with which he/she at risk of colliding. The proposed method was evaluated in an empirical environment, and the results verified its effectiveness.