IROS 2020 论文列表

In this paper an approach for the identification of the dynamic parameters, i.e. base parameters, of rigid robots is presented. By using the polynomial approximation operator, an equation is obtained for the identification of the parameters which solely depends on measurable signals and thereby contains no equation error. The resulting expressions can be evaluated online or offline by filtering the measurable signals with FIR filters. In order to identify the parameters on the basis of measurements, an algorithm is presented to calculate the parameters numerically stable, even if the data is obtained sequentially, without a singular value decomposition. The parameters can be determined meaningfully by considering box constraints in order to ensure physical feasibility. The presented methods are finally used to identify the dynamic parameters of a delta robot and compared to the standard approach.

This study proposes a technique to estimate the output state of twisted string actuators (TSAs) based on payload's acceleration measurements. We outline differential kinematics relationships of the actuator, re-formulate these into a nonlinear parameter identification problem and then apply linearization techniques to efficiently solve it as a quadratic program. Using accurate estimates of string parameters obtained with the proposed method, we can predict TSA position with sub-millimeter accuracy via conventional kinematic relationships. In addition, the proposed method supports accurate estimation under varying operating conditions, unpredictable perturbations, and poorly-excited trajectories. This technique can be employed to improve the accuracy of trajectory tracking when the use of direct position measurements is challenging, with the list of potential applications including flexible and soft robots, long-span cable robots, multi-DOF joints and others.

This paper focuses on the design and comparison of different deep neural networks for the real-time prediction of locomotor intentions by using data from inertial measurement units. The deep neural network architectures are convolutional neural networks, recurrent neural networks, and convolutional recurrent neural networks. The input to the architectures are features in the time domain, which have been derived either from one inertial measurement unit placed on the upper right leg of ten healthy subjects, or two inertial measurement units placed on both the upper and lower right leg of ten healthy subjects. The study shows that a WaveNet, i.e., a full convolutional neural network, achieves a peak F1-score of 87.17% in the case of one IMU, and a peak of 97.88% in the case of two IMUs, with a 5-fold cross-validation.

In this paper, we introduce IDOL, an optimization-based framework for IMU-DVS Odometry using Lines. Event cameras, also called Dynamic Vision Sensors (DVSs), generate highly asynchronous streams of events triggered upon illumination changes for each individual pixel. This novel paradigm presents advantages in low illumination conditions and high-speed motions. Nonetheless, this unconventional sensing modality brings new challenges to perform scene reconstruction or motion estimation. The proposed method offers to leverage a continuous-time representation of the inertial readings to associate each event with timely accurate inertial data. The method's front-end extracts event clusters that belong to line segments in the environment whereas the back-end estimates the system's trajectory alongside the lines' 3D position by minimizing point-to-line distances between individual events and the lines' projection in the image space. A novel attraction/repulsion mechanism is presented to accurately estimate the lines' extremities, avoiding their explicit detection in the event data. The proposed method is benchmarked against a state-of-the-art frame-based visual-inertial odometry framework using public datasets. The results show that IDOL performs at the same order of magnitude on most datasets and even shows better orientation estimates. These findings can have a great impact on new algorithms for DVS.

State-of-the-art approaches for robot navigation among humans are typically restricted to planar movement actions. This work addresses the question of whether it can be beneficial to use interaction actions, such as saying, touching, and gesturing, for the sake of allowing robots to navigate in unstructured, crowded environments. To do so, we first identify challenging scenarios to traditional motion planning methods. Based on the hypothesis that the variation in modality for these scenarios calls for significantly different planning policies, we design specific navigation behaviors as interaction planners for actuated, mobile robots. We further propose a high level planning algorithm for multi-behavior navigation, named Interaction Actions for Navigation (IAN). Through both real-world and simulated experiments, we validate the selected behaviors and the high-level planning algorithm, and discuss the impact of our obtained results on our stated assumptions.

In this paper, we present an optimal control approach using Linear Matrix Inequalities (LMIs) for trajectory tracking control of a three-wheeled omnidirectional mobile robot in the presence of external disturbances on the robot's actuators and noise in the robot's sensor measurements. First, a state-space representation of the omnidirectional robot dynamics is derived using a point-mass dynamic model. Then, we propose an LMI-based full-state feedback H∞-optimal controller for the tracking problem. The robot's tracking performance with the H∞-optimal controller is compared to its performance with a classical full-state feedback tracking controller in simulations with circular and bowtie-shaped reference trajectories. In order to evaluate our proposed controller in practice, we also implement the H∞-optimal and classical controllers for these reference trajectories on a three-wheeled omnidirectional robot. The H∞-optimal controller guarantees stabilization of the robot motion and attenuates the effects of frictional disturbances and measurement noise on the robot's tracking performance. Using the H∞-optimal controller, the robot is able to track the reference trajectories with up to a 47.8% and 45.8% decrease in the maximum pose and twist errors, respectively, over a full cycle of the trajectory compared to the classical controller. The simulation and experimental results show that our LMI-based H∞-optimal controller is robust to undesired effects of disturbances and noise on the dynamic behavior of the robot during trajectory tracking and can outperform the classical controller in attenuating their effects.

Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation. However, standard DRL methods often suffer from poor sample efficiency, partially because they aim to be entirely problem-agnostic. In this work, we introduce a novel approach to exploration and hierarchical skill learning that derives its sample efficiency from intuitive assumptions it makes about the behavior of objects both in the physical world and simulations which mimic physics. Specifically, we propose the Hypothesis Proposal and Evaluation (HyPE) algorithm, which discovers objects from raw pixel data, generates hypotheses about the controllability of observed changes in object state, and learns a hierarchy of skills to test these hypotheses. We demonstrate that HyPE can dramatically improve the sample efficiency of policy learning in two different domains: a simulated robotic blockpushing domain, and a popular benchmark task: Breakout. In these domains, HyPE learns high-scoring policies an order of magnitude faster than several state-of-the-art reinforcement learning methods.

Actuation means for soft robotic structures are manifold: despite actuation mechanisms such as tendon-driven manipulators or shape memory alloys, the majority of soft robotic actuators are fluidically actuated - either purely by positive or negative air pressure or by hydraulic actuation only. This paper presents the novel idea of employing hybrid fluidic - hydraulic and pneumatic - actuation for soft robotic systems. The concept and design of the hybrid actuation system as well as the fabrication of the soft actuator are presented: Polyvinyl Alcohol (PVA) foam is embedded inside a casted, reinforced silicone chamber. A hydraulic and pneumatic robotic syringe pump are connected to the base and top of the soft actuator. We found that a higher percentage of hydraulics resulted in a higher output force. Hydraulic actuation further is able to change displacements at a higher rate compared to pneumatic actuation. Changing between Hydraulic:Pneumatic (HP) ratios shows how stiffness properties of a soft actuator can be varied.

Exploiting contacts with environment structures provides extra force support to a UAV, often reducing the power consumption and hence extending the mission time. This paper investigates one such way to exploit flat surfaces in the environment by a novel aerial-ground hybrid locomotion. Our design is a single passive wheel integrated at the UAV bottom, serving a minimal design to date. We present the principle and implementation of such a simple design as well as its control. Flight experiments are conducted to verify the feasibility and the power saving caused by the ground locomotion. Results show that our minimal design allows successful aerial-ground hybrid locomotion even with a less-controllable bi-copter UAV. The ground locomotion saves up to 77% battery without much tuning effort.

In this study we set out to design a computer vision-based system to assess human-robot trust in real time during close-proximity human-robot collaboration. This paper presents the setup and hardware for an augmented reality-enabled human-robot collaboration cell as well as a method of measuring operator proximity using an infrared camera. We tested this setup as a tool for assessing trust through physical apprehension signals in a collaborative drawing task, where participants hold a piece of paper on a table while the robot draws between their hands. Midway through the test we attempt to induce a decrease in trust with an unexpected change in robot speed and evaluate subject motions along with self-reported trust and emotional arousal through galvanic skin response. After performing the experiment with forty participants, we found that reported trust was significantly affected when robot movement speed was increased. The galvanic skin response measurement were not significantly different between the test conditions. The motion tracking method used in this study did not suggest that subjects' motions were significantly affected by the decrease in trust.

We design and develop a new shared Augmented Reality (AR) workspace for Human-Robot Interaction (HRI), which establishes a bi-directional communication between human agents and robots. In a prototype system, the shared AR workspace enables a shared perception, so that a physical robot not only perceives the virtual elements in its own view but also infers the utility of the human agent-the cost needed to perceive and interact in AR-by sensing the human agent's gaze and pose. Such a new HRI design also affords a shared manipulation, wherein the physical robot can control and alter virtual objects in AR as an active agent; crucially, a robot can proactively interact with human agents, instead of purely passively executing received commands. In experiments, we design a resource collection game that qualitatively demonstrates how a robot perceives, processes, and manipulates in AR and quantitatively evaluates the efficacy of HRI using the shared AR workspace. We further discuss how the system can potentially benefit future HRI studies that are otherwise challenging.

This paper presents a concept for haptic-based human-in-the-loop aerial manipulation for drilling. The concept serves as a case study for designing the human-drone interface to remotely drill with a mobile-manipulating drone. The notion of the work stems from using drones to perform dangerous tasks like material assembly, sensor insertion while being vertically elevated from bridge, wind turbine, and power line. Presented is the aerial manipulator, the customized haptic drill press, the gantry-based test-and-evaluation platform design, material drilling results in the gantry, and validation-and-verification results for indoor flight trials.

Foresighted, human-aware navigation is a prerequisite for service robots acting in indoor environments. In this paper, we present a novel human-aware navigation approach that relies on long-term prediction of human movements. In particular, we consider the problem of finding a path from the robot's current position to the initially unknown navigation goal of a moving user to provide timely assistance there. The navigation strategy has to minimize the robot's arrival time and at the same time comply with the user's comfort during the movement. Our solution predicts the user's navigation goal based on the robot's observations and prior knowledge about typical human transitions between objects. Based on the motion prediction, we then compute a time-dependent cost map that encodes the belief about the user's positions at future time steps. Using this map, we solve the time-dependent shortest path problem to find an efficient path for the robot, which still abides by the rules of human comfort. To identify robot navigation actions that are perceived as uncomfortable by humans, we performed user surveys and defined the corresponding constraints. We thoroughly evaluated our navigation system in simulation as well as in real-world experiments. As the results show, our system outperforms existing approaches in terms of human comfort, while still minimizing arrival times of the robot.

Optimizing lower-body exoskeleton walking gaits for user comfort requires understanding users' preferences over a high-dimensional gait parameter space. However, existing preference-based learning methods have only explored low-dimensional domains due to computational limitations. To learn user preferences in high dimensions, this work presents LINECOSPAR, a human-in-the-loop preference-based framework that enables optimization over many parameters by iteratively exploring one-dimensional subspaces. Additionally, this work identifies gait attributes that characterize broader preferences across users. In simulations and human trials, we empirically verify that LINECOSPAR is a sample-efficient approach for high-dimensional preference optimization. Our analysis of the experimental data reveals a correspondence between human preferences and objective measures of dynamicity, while also highlighting differences in the utility functions underlying individual users' gait preferences. This result has implications for exoskeleton gait synthesis, an active field with applications to clinical use and patient rehabilitation.

Transfer of objects between humans and robots is a critical capability for collaborative robots. Although there has been a recent surge of interest in human-robot handovers, most prior research focus on robot-to-human handovers. Further, work on the equally critical human-to-robot handovers often assumes humans can place the object in the robot’s gripper. In this paper, we propose an approach for human-to-robot handovers in which the robot meets the human halfway, by classifying the human’s grasp of the object and quickly planning a trajectory accordingly to take the object from the human’s hand according to their intent. To do this, we collect a human grasp dataset which covers typical ways of holding objects with various hand shapes and poses, and learn a deep model on this dataset to classify the hand grasps into one of these categories. We present a planning and execution approach that takes the object from the human hand according to the detected grasp and hand position, and replans as necessary when the handover is interrupted. Through a systematic evaluation, we demonstrate that our system results in more fluent handovers versus two baselines. We also present findings from a user study (N = 9) demonstrating the effectiveness and usability of our approach with naive users in different scenarios. More information can be found at http://wyang.me/handovers.

Analysis of human daily living activities, particularly walking activity, is essential for health-care applications such as fall prevention, physical rehabilitation exercises, and gait monitoring. Studying the evolution of the gait cycle using wearable sensors is beneficial for the detection of any abnormal walking pattern. This paper proposes a novel discrete/continuous unsupervised Hidden Markov Model method that is able to recognize six gait phases of a typical human walking cycle through the use of two wearable Inertial Measurement Units (IMUs) mounted at both feet of the subject. The results obtained with the proposed approach were compared to those of well-known supervised and unsupervised segmentation approaches. The obtained results show the efficiency of the proposed approach in accurately recognizing the different gait phases of a human gait cycle. The proposed model allows the consideration of the sequential aspect of the walking gait phases while operating in an unsupervised context that avoids the process of data labeling, which is often tedious and time-consuming, particularly within a massive-data context.

As one of the most promising areas, mobile robots draw much attention these years. Current work in this field is often evaluated in a few manually designed scenarios, due to the lack of a common experimental platform. Meanwhile, with the recent development of deep learning techniques, some researchers attempt to apply learning-based methods to mobile robot tasks, which requires a substantial amount of data. To satisfy the underlying demand, in this paper we build HouseExpo, a large-scale indoor layout dataset containing 35, 126 2D floor plans including 252, 550 rooms in total. Together we develop PseudoSLAM, a lightweight and efficient simulation platform to accelerate the data generation procedure, thereby speeding up the training process. In our experiments, we build models to tackle obstacle avoidance and autonomous exploration from a learning perspective in simulation as well as real-world experiments to verify the effectiveness of our simulator and dataset. All the data and codes are available online and we hope HouseExpo and PseudoSLAM can feed the need for data and benefit the whole community.

A key challenge for an agent learning to interact with the world is to reason about physical properties of objects and to foresee their dynamics under the effect of applied forces. In order to scale learning through interaction to many objects and scenes, robots should be able to improve their own performance from real-world experience without requiring human supervision. To this end, we propose a novel approach for modeling the dynamics of a robot's interactions directly from unlabeled 3D point clouds and images. Unlike previous approaches, our method does not require ground-truth data associations provided by a tracker or any pre-trained perception network. To learn from unlabeled real-world interaction data, we enforce consistency of estimated 3D clouds, actions and 2D images with observed ones. Our joint forward and inverse network learns to segment a scene into salient object parts and predicts their 3D motion under the effect of applied actions. Moreover, our object-centric model outputs action-conditioned 3D scene flow, object masks and 2D optical flow as emergent properties. Our extensive evaluation both in simulation and with real-world data demonstrates that our formulation leads to effective, interpretable models that can be used for visuomotor control and planning. Videos, code and dataset are available at http://hind4sight.cs.uni-freiburg.de.

Grasping can be conceptualized as the ability of an end-effector to temporarily attach or fixture an object to a manipulator-constraining all motion of the workpiece with respect to the end-effector's base frame. This seemingly simplistic action often requires excessive sensing, computation, or control to achieve with multi-fingered hands, which can be mitigated with underactuated mechanisms. In this work, we present the analysis of radial graspers for automated part fixturing and grasping in the plane with a design implementation of a single-actuator, 8-finger gripper. By leveraging a passively adaptable mechanism that is under-constrained pre-contact, the gripper conforms to arbitrary object geometries and locks post-contact as to provide form closure around the object. We also justify that 8 radially symmetric fingers with passive locking are sufficient to create robust form closure grasps on arbitrary planar objects. The underlying mechanism of the gripper is described in detail, with analysis of its highly underactuated nature, and the resulting form closure ability. We show with a wide variety of objects that the gripper is able to acquire robust grasps on all of them, and maintain maximal quality form closure on most objects, with each finger exerting equal grasp force within ±2.48 N.