IROS 2016 论文列表

Robotic tasks are becoming increasingly complex, and with this also the robotic systems. This requires new tools to manage this complexity and to orchestrate the systems to fulfill demanding autonomous tasks. For this purpose, we developed a new graphical tool targeting at the creation and execution of robotic tasks, called RAFCON. These tasks are described in hierarchical state machines supporting concurrency. A formal notation of this concept is given. The tool provides many debugging mechanisms and a GUI with a graphical editor, allowing for intuitive visual programming and fast prototyping. The application of RAFCON for an autonomous mobile robot in the SpaceBotCamp competition has already proved to be successful.

An amphibious all terrain mobile robot is required for disaster response tasks. In this paper, we propose “R-Crank”, which has a simple four wheels driving configuration with crank links, connecting to ipsilateral front and rear wheels so as to form parallel four-bar linkage systems. The crank links act as legs because their trajectory with respect to the ground become trochoid curve, which is commonly used as leg trajectories for a legged robot. These links achieve high terrain adaptability while maintaining simple structure of the wheeled robot. We developed a prototype model and carried out basic experiments. The robot achieved to climb 0.3 m of a step(76.9% of the wheel diameter), stairs and a snowy slope. In addition, we propose amphibious structure of crank links by installing multiple rigid paddles. The propulsive force generated by the crank links was measured and empirically derived the optimum parameters by using a small-sized experimental apparatus. Finally the robot equipped with the amphibious crank links achieved propulsion on water at 0.13 m/s. We also verified that the robot achieved going up and into water through stairs.

This paper proposes a quasi-passive dynamic autonomous control (Q-PDAC) for a three-dimensional (3-D) bipedal gait of humanoid robots from start points to goal points. The major approach for 3-D traveling is currently footstep planning by a constantly stable gait with an emphasis on its accurate and secure traveling. However, energy would potentially be wasted when the robot accurately travels according to the planned footsteps. In contrast, a limit-cycle-based gait possesses the good efficiency by a gait speed control, although the accurate and secure traveling is difficult for it. Its gait speed control is unfortunately not enough to freely travel on 3-D spaces: shortages of a turning speed control, trackability of horizontal speed, and stability of the bipedal gait. Hence, the Q-PDAC supplies three proper angular momenta by hip and ankle joints to achieve the turning motion and enhance the trackability of horizontal motion. Three angular momenta are simply designed consistent in the PDAC dynamics, and achieved the sufficient gait speed control for 3-D traveling. As a result, the robot can efficiently travel from the start point to the goal point while following a leader point not to collide with walls.

One of the standing challenges in multi-robot systems is the ability to reliably coordinate motions of multiple robots in environments where the robots are subject to disturbances. We consider disturbances that force the robot to temporarily stop and delay its advancement along its planned trajectory which can be used to model, e.g., passing-by humans for whom the robots have to yield. Although reactive collision-avoidance methods are often used in this context, they may lead to deadlocks between robots. We design a multi-robot control strategy for executing coordinated trajectories computed by a multi-robot trajectory planner and give a proof that the strategy is safe and deadlock-free even when robots are subject to delaying disturbances. Our simulations show that the proposed strategy scales significantly better with the intensity of disturbances than the naive liveness-preserving approach. The empirical results further confirm that the proposed approach is more reliable and also more efficient than state-of-the-art reactive techniques.

Legged robots such as hexapods have the potential to traverse unstructured terrain. This paper introduces a novel hexapod robot (Weaver) using a hierarchical controller, with the ability to efficiently traverse uneven and inclined terrain. The robot has five joints per leg and 30 degrees of freedom overall. The two redundant joints improve the locomotion of the robot by controlling the body pose and the leg orientation with respect to the ground. The impedance controller in Cartesian space reacts to unstructured terrain and thus achieves self-stabilizing behavior without prior profiling of the terrain through exteroceptive sensing. Instead of adding force sensors, the force at the foot tip is calculated by processing the current signals of the actuators. This work experimentally evaluates Weaver with the proposed controller and demonstrates that it can effectively traverse challenging terrains and high gradient slopes, reduce angular movements of the body by more than 55% and reduce the cost of transport (up to 50% on uneven terrain and by 85% on a slope with 20 °). The controller also enables Weaver to walk up inclines of up to 30 °, and remain statically stable on inclines up to 50 °. Furthermore, we present a new metric for legged robot stability performance along with a method for proprioceptive terrain characterization.

An octopus arm has no rigid structure, it is mostly composed of muscles aligned in various directions and the nerves. The muscles are roughly aligned in three directions, and by driving the muscles selectively, the octopus arm can perform multiple functions such as the contracting, bending, torsion and stiffness alteration. This study aims at the development of a new flexible robotic arm using thin McKibben actuators mimicking the muscle structure of an octopus arm. The McKibben actuator is a well-known pneumatic artificial muscle, and we have developed extremely thin McKibben actuators by using a braiding machine. In this paper, configuration of the flexible arm is proposed. The developed mechanism consists of thirty two thin McKibben actuators arranged in three directions, axial, radial and oblique, imitating the muscle structure of an actual octopus arm. The fundamental motion of the flexible arm is investigated experimentally. The proposed mechanism performs bending, contracting, torsion movements and stiffness alteration like an octopus arm.

There are no mechanical harvesters for the fresh market apple industry commercially available. The absence of automated harvesting technology is a critical problem because of rising production costs and increasing uncertainty about future labor availability. This paper presents the preliminary design of a robotic apple harvester. The approach adopted was to develop a low-cost, `undersensed' system for modern orchard systems with fruiting wall architectures. A machine vision system fuses Circular Hough Transform and blob analysis to detect clustered and occluded fruit. The design includes a custom, six degree of freedom manipulator with an underactuated, passively compliant end-effector. After fruit localization, the system makes a linear approach to the apple and replicates the human picking process. Integrated testing of the robotic harvesting system has been completed in a laboratory environment with a replica apple tree for proof-of-concept demonstration. Experimental results show that the system picked 95 of the 100 fruit attempted with average localization and picking times of 1.2 and 6.8 seconds, respectively, per fruit. Additional work planned in preparation for field evaluation in a commercial orchard is also described.

This paper describes a novel methodology for programming grinding tool-paths, tool-path orientations and grinding strategies based on the captured trajectories of a surface finishing tool operated by the Skilled-Operator. In order to extract the grinding parameters and strategy from the trajectory of the skilled operator, the manual tool-path is first segmented into tool-path primitives. The order of the manual tool-path primitives will form the grinding strategy. Next, the robotic tool-path primitives are then generated based on the boundaries of the manual tool-path primitive in a computer-aided-manufacturing software. The orientations of the manual tool-path are used to anchor the orientations of the robotic tool-path. Spherical linear interpolation and spherical spline quaternion interpolation are used to interpolate the orientations for the robotic tool-path points along the cross curves, followed by the flow curves respectively. The programmed robotic tool-paths generated were subsequently applied and proven to be able to grind the work-piece to the desired profile within the desired tolerance.

We present a method for multi-class segmentation from RGB-D data in a realistic warehouse picking setting. The method computes pixel-wise probabilities and combines them to find a coherent object segmentation. It reliably segments objects in cluttered scenarios, even when objects are translucent, reflective, highly deformable, have fuzzy surfaces, or consist of loosely coupled components. The robust performance results from the exploitation of problem structure inherent to the warehouse setting. The proposed method proved its capabilities as part of our winning entry to the 2015 Amazon Picking Challenge. We present a detailed experimental analysis of the contribution of different information sources, compare our method to standard segmentation techniques, and assess possible extensions that further enhance the algorithm's capabilities. We release our software and data sets as open source.

Legged robots require a robust and fast responding feet contact detection strategy. Common force sensors are often too heavy and can be easily damaged during impacts with the terrain. Therefore, it is desirable to detect a contact without a force sensor. This paper introduces a probabilistic contact detection strategy which considers full dynamics and differential/forward kinematics to maximize the use of available information for contact estimation. This papers shows that such strategy is much more accurate than the state-of-the-art strategy that only take one measure into account, with a quadrupedal robot.

Learning sequential force interaction tasks from kinesthetic demonstrations is a promising approach to transfer human manipulation abilities to a robot. In this paper we propose a novel concept to decompose such demonstrations into a set of Movement Primitives (MPs). The decomposition is based on a probability distribution we call Directional Normal Distribution (DND). To capture the sequential properties of the manipulation task, we model the demonstrations with a Hidden Markov Model (HMM). Here, we employ mixtures of DNDs as the HMM's output emissions. The combination of HMMs and mixtures of DNDs allows to infer the MP's composition, i.e., its coordinate frames, control variables and target coordinates from the demonstration data. In addition, it permits to determine an appropriate number of MPs that explains the demonstrations best. We evaluate the approach on kinesthetic demonstrations of a light bulb unscrewing task. Decomposing the task leads to intuitive and meaningful MPs that reflect the natural structure of the task.

Sound source localization (SSL) is an essential technique in many applications, such as robot audition, human-robot interaction and speech capturing. However, SSL from a binaural input is still a challenging problem, particularly when multiple sources are active simultaneously. In this work, we propose a multi-sources localization framework based on the time-delay compensation (TDC) estimator and clustering analysis. The TDC estimator is a simultaneous operator to estimate binaural cues, which breaks the limitation of independent processors for binaural cues extraction. The multi-sources decision is realized by clustering analysis for the binaural cues of multiple signal frames. In experiments, we demonstrate that the localization performance is improved compared to the methods that assume the number of spatial stationary sources to be known. Results with both simulated and recorded impulse responses show that robust performance can be achieved with limited prior training, and our method is also adaptive to different sound activities.

Nowadays, agricultural and mining industry applications require saving energy in mobile robotic tasks. This critical issue encouraged us to enhance the performance of path tracking controllers during manoeuvring over slippery and rough terrains. In this scenario, we propose probabilistic approaches under machine learning schemes in order to optimally self-tune the controller. The approaches are real time implemented and tested in a mining machinery skid steer loader Cat® 262C under gravel and muddy terrains (and their transitions). Finally, experimental results presented in this work show that the performance of the controller enhances up to 20% (average) without compromising saturations in the actuators.

The paper proposes a system for mapping the 3D location of a sound source using data from a microphone array, each of which gives an independent estimate of the direction. LiDAR is used to generate a 3D map of the environment and to estimate the location of the sensor in six degrees of freedom (6-DoF). By combing these modules, our system determines the direction to a sound source in 3D global space for a moving robot. From evaluation of the time series of the tracked sound stream, the position of the sound source is estimated by using the Monte Carlo localization approach. When estimated from a moving robot, an approach based on triangulation does not always adequately locate a sound source, because the estimate depends on the relationship between the location of the source and that of the moving robot. The main advantage of the proposed system is that as an audible signal is perceived, it continuously estimates the location of the source. We evaluate the system by performing an experiment using a hand-held sensor.

Impact protection and vibration isolation are an important component of the mobile robot designer's toolkit; however, current damping materials are available only in bulk or molded form, requiring manual fabrication steps and restricting material property control. In this paper we demonstrate a new method for 3D printing viscoelastic materials with specified material properties. This method allows arbitrary net-shape material geometries to be rapidly fabricated and enables continuously varying material properties throughout the finished part. This new ability allows robot designers to tailor the properties of viscoelastic damping materials in order to reduce impact forces and isolate vibrations. We present a case study for using this material to create jumping robots with programmed levels of bouncing.

This paper describes a new task-oriented grasping method to reorient a rigid object to its nominal pose, which is defined as the configuration that it needs to be grasped from, in order to successfully execute a particular manipulation task. Our method combines two key insights: (1) a visual 6 Degree-of-Freedom (DoF) pose estimation technique based on 2D-3D point correspondences is used to estimate the object pose in real-time and (2) the rigid transformation from the current to the nominal pose is computed online and the object is reoriented over a sequence of steps. The outcome of this work is a novel method that can be effectively used in the preparatory phase of a manipulation task, to permit a robot to start from arbitrary object placements and configure the manipulated objects to the nominal pose, as required for the execution of a subsequent task. We experimentally demonstrate the effectiveness of our approach on a full-size humanoid robot (WALK-MAN) using different objects with various pose settings under real-time constraints.

This paper presents the experimental validation of a novel control strategy that unifies the entire gait cycle of a powered knee-ankle prosthetic leg without the need to switch between controllers for different periods of gait. Current control methods divide the gait cycle into several sequential periods each with independent controllers, resulting in many patient-specific control parameters and switching rules that must be tuned for a specific walking speed. The single controller presented is speed-invariant with a minimal number of control parameters to be tuned. A single, periodic virtual constraint is derived that exactly characterizes the desired actuated joint motion as a function of a mechanical phase variable across walking cycles. A single sensor was used to compute a phase variable related to the residual thigh angle's phase plane, which was recently shown to robustly represent the phase of non-steady human gait. This phase variable allows the prosthesis to synchronize naturally with the human user for intuitive, biomimetic behavior. A custom powered knee-ankle prosthesis was designed and built to implement the control strategy and validate its performance. A human subject experiment was conducted across multiple walking speeds (1 to 3 miles/hour) in a continuous sequence with the single phase-based controller, demonstrating its adaptability to the user's intended speed.

This paper reports on a data-driven motion planning approach for interaction-aware, socially-compliant robot navigation among human agents. Autonomous mobile robots navigating in workspaces shared with human agents require motion planning techniques providing seamless integration and smooth navigation in such. Smooth integration in mixed scenarios calls for two abilities of the robot: predicting actions of others and acting predictably for them. The former requirement requests trainable models of agent behaviors in order to accurately forecast their actions in the future, taking into account their reaction on the robot's decisions. A human-like navigation style of the robot facilitates other agents—most likely not aware of the underlying planning technique applied—to predict the robot motion vice versa, resulting in smoother joint navigation. The approach presented in this paper is based on a feature-based maximum entropy model and is able to guide a robot in an unstructured, real-world environment. The model is trained to predict joint behavior of heterogeneous groups of agents from onboard data of a mobile platform. We evaluate the benefit of interaction-aware motion planning in a realistic public setting with a total distance traveled of over 4 km. Interestingly the motion models learned from human-human interaction did not hold for robot-human interaction, due to the high attention and interest of pedestrians in testing basic braking functionality of the robot.

A precise and efficient tracking technique is essential for an intelligent vehicle to interact with the surrounding vehicles on the road. In this paper, we propose a model-based vehicle tracking method using the Rao-Blackwellized particle filter (RBPF) and scaling series particle filter (SSPF).