IROS 2017 论文列表

This paper presents MTF - a modular, extensible and highly efficient open source framework for registration based tracking targeted at robotics applications. It is implemented entirely in C++ and is designed from the ground up to easily integrate with systems that support any of several major vision and robotics libraries including OpenCV, ROS, ViSP and Eigen. It is also faster and more precise than other existing tracking systems. In order to establish the theoretical basis for its design, a new way to conceptualize registration based trackers is also introduced that decomposes tracking into three sub modules - Search Method, Appearance Model and State Space Model. Along with being a practical solution for fast and high precision tracking, this framework can also serve as a useful research tool by allowing existing and new methods for any of the sub modules to be studied better. Through extensive use of generic programming, the system makes it easy to plug in a new method for any of the sub modules so that it can not only be tested comprehensively with existing methods but also become immediately available for deployment in any project that uses the framework.

Physical connectors which have geometry to passively guide mating increases robustness in attachments. This is a key design area for self-reconfigurable modular robots, which frequently make and break connections. By repurposing the interpretation of a well-known motion planning tool in configuration space obstacles for its encoding of contact geometry, we present a method for determining a metric of error tolerance (area of acceptance) in multiple dimensions by construction. Watershed analysis is run on this configuration-space model to determine the full shape and area of the capture region for the connector pair. We show the results of this process for several connector types.

The da Vinci Research Kit (DVRK) is a telerobotic surgical research platform endowed with an open controller that allows position, velocity and current control. We consider the problem of modelling and identification of both the Patient Side Manipulators (PSMs) and of the Master Tool Manipulators (MTMs) of the platform. This problem is relevant when realistic dynamic simulations have to be performed using standard software tools, but also for the design of model-based control laws, and for the implementation of sensorless strategies for collision detection or contact force estimation. A LMI-based approach is used for the identification of the robot dynamics in order to guarantee the physical feasibility of the parameters that is not ensured by standard least-squares methods. The identified models are validated experimentally.

The planar rimless wheel (PRW) is a classic and simple passive dynamic mechanism to simulate biped walking, different simplified PRW models have respective descriptions and limited applications. This paper focus on constructing the general PRW model, and analyzing the intrinsic and mathematical relation between different PRW models. Based that, the limit cycle of symmetric PRW and asymmetric PRW are proposed separately. Moreover, the stability in universal domain are investigated in detail. Furthermore, simulation and experiment results show that the 2-period limit cycle motion of the asymmetric PRW is more effective, flexible and self-adaptive compared with regular rimless wheel, and more actual applications would be achieved by adopting the general model.

LiDAR scanners are commonly used for mapping and localization with mobile robots. But, they cannot see through occlusions, as it occurs in harsh environments, containing smoke, fog or dust. Radar scanners can overcome this problem, but they have lower range and angular resolution, and cannot represent an environment in the same quality. In the following article, we present the integration of fused LiDAR and radar data into a SLAM cycle and continue our work from [1], where we presented first results regarding a feature based and a scan matching-based approach for SLAM in environments with changing visibility using LiDAR and radar sensors. New content in this article, the data fusion takes place on scan level as well as on map level and aims to result in an optimum map quality considering the visibility situation. Additionally, we collected more data during an indoor experiment involving real fog (see Fig. 1). Besides the structure of the environment, we can model aerosol concentration with fused LiDAR and Radar data in parallel to the mapping process with a finite difference model without involving a smoke or gas sensor. Overall, our method allows the modeling of the structure of an environment including dynamic distribution of aerosol concentration.

In robot to human object handover, the configuration (position and orientation) in which the object is transferred should be selected so that the handover is safe and comfortable for the human. The trajectory on which the robot moves the object to the point of transfer should be also selected so that the robot intention is clear and the handover feels natural to the human. In this paper, we propose to select the configuration for the transfer and the trajectory to reach this configuration based on what humans do in human-human handovers. We describe a human study designed to investigate the human-human handover and propose an ergonomic model that can predict object transfer position observed in the study. A human-robot experiment is then conducted that shows that the proposed model generates transfer positions that match the preferred height and distance relative to the human.

This paper discusses the condition necessary for achieving stable sliding passive-dynamic walking of a compass-like biped robot with semicircular feet, and analyzes the fundamental gait properties through numerical simulations. First, we introduce the semicircular-footed compass model and develop the equation of motion, holonomic constraint condition, and equation of collision considering the effect of impulsive frictional force. The paradox in transformation of the impulsive frictional force effect is also discussed. Second, we numerically show that short- and long-period sliding passive compass gaits can be generated under the same condition except the initial condition, and the sliding directions of the fore foot immediately after impact in the two gaits are different from each other. Furthermore, we conduct parametric studies to understand the change tendency of the fundamental gait properties with respect to the system parameters such as the foot radius and frictional coefficient. The simulation results show that the effect of semicircular feet makes it possible for the passive biped to walk on slippery downhill stably in the absence of the hip-damper.

Soft manipulators have been a rising focus of soft robotics research. Taking advantage of soft materials and flexible, continuous movements, they have promising applicable prospect. However, their highly internal nonlinearity and unpredictable deformation caused by environmental effects make it difficult to build an exact model for control. In this work, we propose a generalized controller for soft manipulators using an estimated Jacobian-based model derived from structural analysis. The model can be simplified from reasonable assumptions of manipulator structure, and updated to balance conformity to reality and stability. In prototype experiments on an 3D multi-segment soft manipulator, the control method exhibits accuracy as well as adaptability to self gravity and external loads.

Most control methods of soft manipulators are developed based on physical models derived from mathematical analysis or learning methods. However, due to internal nonlinearity and external uncertain disturbances, it is difficult to build an accurate model, further, these methods lack robustness and portability among different prototypes. In this work, we propose a model-free control method based on reinforcement learning and implement it on a multi-segment soft manipulator in 2D plane, which focuses on the learning of control strategy rather than the physical model. The control strategy is validated to be effective and robust in prototype experiments, where we design a simulation method to speed up the training process.

The proposed work deals with robotic unfolding of a garment that has been placed flat on a table and folded over a certain axis. The algorithm combines image and depth data to detect the bottom and top (folded) layer of the garment. The detection is formulated as a labeling of the garment surface and solved in an energy minimization framework. Once the garment pose is known, several candidate folding axes are generated and used to unfold the garment virtually. The correct folding axis is selected from these candidate axes. The method does not set any constraints on the garment shape; thus it can deal with various types of garments including jackets, pants, shorts, skirts or T-shirts of any sleeve lengths. The garment is unfolded by the dual-arm robot. One arm grasps boundary of the top layer and brings it over the estimated folding axis, while the second arm is holding the bottom layer to prevent the garment from slipping. The perception procedure was tested on the annotated dataset that we are making publicly available. The experimental evaluation of the robotic manipulation is also provided.

Estimating the pose of orbiting satellites is a key prerequisite for supporting autonomous proximity operations in space. This work presents a monocular 3D tracking algorithm that tracks edges with the aid of an arbitrary 3D mesh model assumed to capture a satellite's shape. The proposed tracker propagates a pose hypothesis between successive frames, using it first to render a depth image and then refining it according to partial matches established between depth and intensity edges. Edge matching relies on fast, local 1D searches along the depth gradient direction. The tracker does not require any pre-processing of the 3D model nor does it make any assumptions regarding its characteristics, as is often the case for other approaches. It is also robust to parts of the tracked satellite being out of view, occluded, shadowed or visually undetected. Experimental results evaluating the accuracy of the tracker and comparing it with established techniques are also included.

Robust state estimation and real-time dense mapping are two core capabilities for autonomous navigation of mobile robots. Global Navigation Satellite System (GNSS) and visual odometry/SLAM are popular methods for state estimation. However, when working between tall buildings or in indoor environments, GNSS fails due to limited sky view or obstruction from buildings. Visual odometry/SLAM are prone to long-term drifting in the absence of reliable loop closure detection. A state estimation method with global-consistent guarantee is desirable for navigation applications. As for real-time mapping, SLAM methods usually get a sparse map that is not good enough for obstacle avoidance and path-planning, and high-quality dense mapping is often computationally too demanding for mobile devices. Realizing the availability of city-scale 3D models, in this work, we improve our previous work on model-based global localization, and propose a model-aided monocular visual-inertial state estimation and dense mapping solution. We first develop a global-consistent state estimator by fusing visual-inertial odometry with the model-based localization results. Utilizing depth prior from the model, we perform motion stereo with semi-global disparity smoothing. Our dense mapping pipeline is capable of online detection of obstacles that are originally not included in the offline 3D model. Our method runs onboard an embedded computer in real-time. We validate both the state estimation and mapping accuracy in real-world experiments.

Model Predictive Control is becoming more and more present in robotic applications. It has been successfully used in control of humanoid robots to adjust positions of the footsteps in order to satisfy stability constraints. In this paper we show how to adapt such scheme for a quadruped robot utilizing a static walking. The MPC is used to provide a center of mass projection reference, keeping it within support polygons to ensure stability. User is given freedom in choosing the desired dynamical behavior of the reference. The proposed control framework is tested in simulation and on a real quadruped robot. An emphasize is put on generality of such approach which is independent of gait parameters.

Mission planning and execution for autonomous vehicles is crucial for their effective and efficient operation during scientific exploration, or search and rescue missions, to mention a few. Automated Planning has shown to be a useful tool for “high level” mission planning, that is, allocating tasks to vehicles while following given constraints (e.g., energy, collision avoidance). In this paper, we focus on making mission planning flexible and robust. That is, a human mission coordinator can modify tasks during the mission execution, so the tasks have to be dynamically reallocated during the process. Moreover, we assume that communication might not be reliable when vehicles are “outside”, i.e., performing the tasks, and thus we enforce vehicles to come back to their safe spots regularly. To address these requirements, we have developed two models, namely “all tasks” and “one round”, and integrated them to the control software. We have evaluated our approach in a field experiment focused on a mine-hunting scenario.

This paper presents a mission planning problem for a cooperative team of unmanned ground vehicles (UGVs), which includes multiple rovers and a solar-powered mobile charging station. The team is required to start at an initial point and visit a series of objective points before arriving at the final point selected from the set of objective points, where the UGVs will be charged from the solar-powered mobile charging station. This mission is represented as a multi-Hamiltonian Path Problem (mHPP). In order to effectively coordinate the team, an understanding of the mission environment is first obtained by generating a scalar field representation of the solar insolation of the environment from a visual-spectrum image. Then, a cascaded heuristic optimization algorithm, using modified genetic algorithm and particle swarm optimization, is used to generate a time-optimized mission plan for the team of UGVs, which guides each UGV to its assigned objective points and then rendezvous at the final charging location while guaranteeing compliance with the net energy gain constraint. The feasibility and efficiency of the proposed algorithm are verified using an experimental testbed and constructed indoor simulation environments.

To develop a multi-modal in-traffic bridge deck scanning device, we need to estimate the relative pose between a ground penetrating radar (GPR) and a camera. Unlike camera images, GPR output is in a non-Euclidean coordinate system because it only detects underground objects relative to road surface. When road surface is non-planar, its output cannot be trivially mapped to a 3D Cartesian system which is necessary for sensor fusion. Since there is no joint coverage between two sensors due to mounting requirements, we design an artificial planar bridge assisted by a planar mirror as the calibration rig. We combine the pinhole camera model with mirror reflection transformation and model the GPR imaging process. We estimate the camera and mirror poses and extract readings from hyperbolas generated from metal balls. We employ the maximum likelihood estimator to estimate the rigid body transformation between the two sensors and provide the closed form error analysis. We have conducted physical experiments to validate our calibration process and shown the average error of 6.67 mm for our calibration model. The result is satisfying considering the GPR signal wave length is 18.75 cm.

The Robot Operating System (ROS) is nowadays one of the most popular frameworks for developing robotic applications. To ensure the (much needed) dependability and safety of such applications we forecast an increasing demand for ROS-specific coding standards, static analyzers, and tools alike. Unfortunately, the development of such standards and tools can be hampered by ROS modularity and configurability, namely the substantial number of primitives (and respective variants) that must, in principle, be considered. To quantify the severity of this problem, we have mined a large number of existing ROS packages to understand how its primitives are used in practice, and to determine which combinations of primitives are most popular. This paper presents and discusses the results of this study, and hopefully provides some guidance for future standardization efforts and tool developers.

Minimally invasive surgery in confined spaces often requires the coordinated use of endoscopes and surgical tools while minimizing visual occlusions. In a robotic system such visual occlusion avoidance has to be achieved autonomously while keeping the surgical end-effector as close as possible to the center of the field of view of the endoscope. This paper presents an investigation of use of redundancy resolution to solve the problem of visual occlusion. Specifically, the paper addresses hard cases where a continuum robot or an ablation catheter emanate from a narrow access channel containing an endoscope. A redundancy resolution method accounting for the kinematics of the continuum robot and allowing for rotation of an angled lens endoscope is presented. A potential field method is used to guide all portions of the continuum arm outside of the visualization cone of the endoscope and a gradient descent method is used to guide the rotation of the endoscope to keep the end-effector as close as possible to the center of the visual field of the endoscope. A simulation case study demonstrates the utility of our method using a recently designed transurethral bladder cancer surgery system as a demonstration platform. Although the context of the problem is bladder surgery utilizing a continuum robot, the method can be generalized to any redundant robot that requires to accomplish a task with minimal visual occlusion.

Human-centered environments are rich with a wide variety of spatial relations between everyday objects. For autonomous robots to operate effectively in such environments, they should be able to reason about these relations and generalize them to objects with different shapes and sizes. For example, having learned to place a toy inside a basket, a robot should be able to generalize this concept using a spoon and a cup. This requires a robot to have the flexibility to learn arbitrary relations in a lifelong manner, making it challenging for an expert to pre-program it with sufficient knowledge to do so beforehand. In this paper, we address the problem of learning spatial relations by introducing a novel method from the perspective of distance metric learning. Our approach enables a robot to reason about the similarity between pairwise spatial relations, thereby enabling it to use its previous knowledge when presented with a new relation to imitate. We show how this makes it possible to learn arbitrary spatial relations from non-expert users using a small number of examples and in an interactive manner. Our extensive evaluation with real-world data demonstrates the effectiveness of our method in reasoning about a continuous spectrum of spatial relations and generalizing them to new objects.