ICRA 2017 Papers

Loop closure detection or place recognition is a fundamental problem in robot simultaneous localization and mapping (SLAM). SeqSLAM is considered to be one of the most successful algorithms for loop closure detection as it has been demonstrated to be able to handle significant environmental condition changes including those due to illumination, weather, and time of the day. However, SeqSLAM relies heavily on exhaustive sequence matching, a computationally expensive process that prevents the algorithm from being used in dealing with large maps. In this paper, we propose Fast-SeqSLAM, an efficient version of SeqSLAM. Fast-SeqSLAM has a much reduced time complexity without degrading the accuracy, and this is achieved by using an approximate nearest neighbor (ANN) algorithm to match the current image with those in the robot map and extending the idea of SeqSLAM to greedily search a sequence of images that best match with the current sequence. We demonstrate the effectiveness of our Fast-SeqSLAM algorithm in appearance based loop closure detection.

We present a framework for fast target detection in real-world robotics applications. Considering that an intelligent agent attends to a task-specific object target during execution, our goal is to detect the object efficiently. We propose the concept of early recognition, which influences the candidate proposal process to achieve fast and reliable detection performance. To check the target constraints efficiently, we put forward a novel policy which generates a sub-optimal checking order, and we prove that it has bounded time cost compared to the optimal checking sequence, which is not achievable in polynomial time. Experiments on two different scenarios: 1) rigid object and 2) non-rigid body part detection validate our pipeline. To show that our method is widely applicable, we further present a human-robot interaction system based on our non-rigid body part detection.

The recent activity in the area of autonomous vehicle navigation has initiated a series of reactions that stirred the automobile industry, pushing for the fast commercialization of this technology which, until recently, seemed futuristic. The LiDAR sensor is able to provide a detailed understanding of the environment surrounding the vehicle making it useful in a plethora of autonomous driving scenarios. Segmenting the 3D point cloud that is provided by modern LiDAR sensors, is the first important step towards the situational assessment pipeline that aims for the safety of the passengers. This step needs to provide accurate segmentation of the ground surface and the obstacles in the vehicle's path, and to process each point cloud in real time. The proposed pipeline aims to solve the problem of 3D point cloud segmentation for data received from a LiDAR in a fast and low complexity manner that targets real world applications. The two-step algorithm first extracts the ground surface in an iterative fashion using deterministically assigned seed points, and then clusters the remaining non-ground points taking advantage of the structure of the LiDAR point cloud. Our proposed algorithms outperform similar approaches in running time, while producing similar results and support the validity of this pipeline as a segmentation tool for real world applications.

This paper considers the problem of safe mission planning of dynamic systems operating under uncertain environments. Much of the prior work on achieving robust and safe control requires solving second-order cone programs (SOCP). Unfortunately, existing general purpose SOCP methods are often infeasible for real-time robotic tasks due to high memory and computational requirements imposed by existing general optimization methods. The key contribution of this paper is a fast and memory-efficient algorithm for SOCP that would enable robust and safe mission planning on-board robots in realtime. Our algorithm does not have any external dependency, can efficiently utilize warm start provided in safe planning settings, and in fact leads to significant speed up over standard optimization packages (like SDPT3) for even standard SOCP problems. For example, for a standard quadrotor problem, our method leads to speedup of 1000× over SDPT3 without any deterioration in the solution quality. Our method is based on two insights: a) SOCPs can be interpreted as optimizing a function over a polytope with infinite sides, b) a linear function can be efficiently optimized over this polytope. We combine the above observations with a novel utilization of Wolfe's algorithm [1] to obtain an efficient optimization method that can be easily implemented on small embedded devices. In addition to the above mentioned algorithm, we also design a two-level sensing method based on Gaussian Process for complex obstacles with non-linear boundaries such as a cylinder.

In this paper we propose an efficient solution to jointly estimate the camera motion and a piecewise-rigid scene flow from an RGB-D sequence. The key idea is to perform a two-fold segmentation of the scene, dividing it into geometric clusters that are, in turn, classified as static or moving elements. Representing the dynamic scene as a set of rigid clusters drastically accelerates the motion estimation, while segmenting it into static and dynamic parts allows us to separate the camera motion (odometry) from the rest of motions observed in the scene. The resulting method robustly and accurately determines the motion of an RGB-D camera in dynamic environments with an average runtime of 80 milliseconds on a multi-core CPU. The code is available for public use/test.

In the Multi-Policy Decision Making (MPDM) framework, a robot's policy is elected by sampling from the distribution of current states, predicting future outcomes through forward simulation, and selecting the policy with the best expected performance. Electing the best plan depends on sampling initial conditions with influential (very high costs) outcomes. Discovering these configurations through random sampling may require drawing many samples, which becomes a performance bottleneck. In this paper, we describe a risk-aware approach which augments this sampling with an optimization process that helps discover those influential outcomes. We describe how we overcome several practical difficulties with this approach, and demonstrate significant performance improvements on a real robot platform navigating a semi-crowded, highly dynamic environment.

This paper describes visual route following for a cliff-climbing, tethered mobile robot for the purpose of autonomously traversing extreme terrain in the presence of obstacles. When the robot's tether contacts an obstacle, an intermediate anchor is formed. In order to detach from intermediate anchors and avoid entanglement, the robot must backtrack along its outgoing trajectory. We use the Visual Teach & Repeat (VT&R) algorithm to autonomously repeat a manually taught path. However, our problem is complicated by the fact that the robot's tether must (i) remain taut regardless of inclination, (ii) allow the robot to drive freely, and (iii) provide motion assistance when wheel traction is reduced on steep slopes. To enable visual route following over varied terrain, we have developed a novel tether controller that selects a safe, steady-state tension based on the robot's inclination while also accounting for vehicle motion. Experiments are performed on our Tethered Robotic Explorer (TReX), which autonomously repeats paths while tethered in both flat-indoor and steep-outdoor environments in the presence of obstacles.

In this paper, we describe the fabrication and testing of a stretchable fabric sleeve with embedded elastic strain sensors for state reconstruction of a soft robotic joint. The strain sensors are capacitive and composed of graphite-based conductive composite electrodes and a silicone elastomer dielectric. The sensors are screenprinted directly into the fabric sleeve, which contrasts the approach of pre-fabricating sensors and subsequently attaching them to a host. We demonstrate the capabilities of the sensor-embedded fabric sleeve by determining the joint angle and end effector position of a soft pneumatic joint with similar accuracy to a traditional IMU. Furthermore, we show that the sensory sleeve is capable of capturing more complex material states, such as fabric buckling and non-constant curvatures along linkages and joints.

In GPS-denied environments, robot systems typically revert to navigating with dead-reckoning and relative mapping, accumulating error in their global pose estimate. In this paper, we propose Feature-based Localization between Air and Ground (FLAG), a method for computing global position updates by matching features observed from ground to features in an aerial image. Our method uses stable, descriptorless features associated with vertical structure in the environment around a ground robot in previously unmapped areas, referencing only overhead imagery, without GPS. Multiple-hypothesis data association with a particle filter enables efficient recovery from data association error and odometry uncertainty. We implement a stereo system to demonstrate our vertical feature based global positioning approach in both indoor and outdoor scenarios, and show comparable performance to laser-scan-matching results in both environments.

Biologists proposed the tau theory to explain how animals control their motion using visual feedback for different tasks including landing and perching. Tau theory is based on a concept called time-to-contact, which is the required time to contact an object if the current velocity is maintained. Recently, tau theory has been applied to control robots' motion for similar tasks such as perching, docking, braking, or landing. However, existing tau theory can only work for the case with zero contact velocity. Some tasks such as perching actually require a non-zero contact velocity to make gripping mechanisms work. To address this problem, we extend the tau theory by proposing a two-stage strategy in one dimensional space to generate the reference trajectory for time-to-contact. Moreover, we propose a new coupling strategy to deal with the motion in three dimensional space. Simulation results demonstrate the effectiveness of proposed two-stage and coupling strategies. Moreover, we leverage a featureless method to estimate the time-to-contact from image sequences and implement it on a mobile robot platform. Experimental results also demonstrate that the non-zero contact velocity can be accomplished using onboard vision feedback. The research presented in this paper can be readily applied to control the motion of flying robots for perching with visual feedback.

Present image based visual servoing approaches rely on extracting hand crafted visual features from an image. Choosing the right set of features is important as it directly affects the performance of any approach. Motivated by recent breakthroughs in performance of data driven methods on recognition and localization tasks, we aim to learn visual feature representations suitable for servoing tasks in unstructured and unknown environments. In this paper, we present an end-to-end learning based approach for visual servoing in diverse scenes where the knowledge of camera parameters and scene geometry is not available a priori. This is achieved by training a convolutional neural network over color images with synchronised camera poses. Through experiments performed in simulation and on a quadrotor, we demonstrate the efficacy and robustness of our approach for a wide range of camera poses in both indoor as well as outdoor environments.

An MRI-actuated catheter is a novel robotic catheter system that utilizes the MRI for both remote steering and visualization for catheter ablation of atrial fibrillation. Planning and control of the catheter requires a sufficiently fast yet accurate model of the catheter. The pseudo-rigid-body (PRB) model offers a reasonable trade-off between speed and accuracy by approximating the continuum catheter as rigid links connected by flexible joints, thus reducing the infinite degrees of freedom of the continuum mechanism to a finite one. In this paper, a PRB model of the MRI-actuated catheter is validated experimentally by comparing the deflections of the PRB model with the deflections of the catheter prototype.

In this work we investigate the identification of a motion model for an autonomous underwater vehicle by applying different machine learning (ML) regression methods. By using the data collected from the robot's on-board navigation sensors, we train the regression models to learn the damping term which is regarded as one of the most uncertain components of the motion model. Four regression techniques are investigated namely, artificial neural networks, support vector machines, kernel ridge regression, and Gaussian processes regression. The performance of the identified models is tested through real experimental scenarios performed with the AUV Leng. The novelty of this work is the identification of an underwater vehicle's motion model, for the first time, through machine learning methods by using the robot's onboard sensory data. Results show that the damping model learned with nonlinear methods yield better estimates than the simplified linear and quadratic model which is identified with least-squares technique.

Stroke is the leading cause of adult disability. Many robots have been developed to administer movement therapies or provide physical assistance to stroke survivors suffering from movement deficits. One effective approach has been to support the weight of the arm, offloading shoulder abductor muscles that have become coupled to elbow muscles. However, patients have limited access to such robots due to the robots' complexity, cost, and bulk. To counter this problem, we developed a lightweight (350 g), inexpensive external actuator, which we call an exomuscle. We constructed a prototype exomuscle by reinforcing a plastic bladder with a fabric bag that is sewn to supporting straps. The bladder can then be inflated with pressurized air to provide expansive forces between the user's torso and arm, supporting shoulder abduction. A seam acting as a hinge joint connects the exomuscle to the torso. We demonstrate that our exomuscle reduces muscular effort by 74% in isometric tasks and 72% in dynamic reaching tasks while minimally affecting the range of motion of the shoulder and elbow (average 4% reduction) on three users ranging from 165 to 188 cm tall. Future studies will evaluate the exomuscle with users who have post-stroke motor impairments.

Hamilton-Jacobi (HJ) reachability is a method that provides rigorous analyses of the safety properties of dynamical systems. These guarantees can be provided by the computation of a backward reachable set (BRS), which represents the set of states from which the system may be driven into violating safety properties despite the system's best effort to remain safe. Unfortunately, the complexity of the BRS computation scales exponentially with the number of state dimensions. Although numerous approximation techniques are able to tractably provide conservative estimates of the BRS, they often require restrictive assumptions about system dynamics without providing an exact solution. In this paper we propose a general method for decomposing dynamical systems. Even when the resulting subsystems are coupled, relatively high-dimensional BRSs that were previously intractable or expensive to compute can now be quickly and exactly computed in lower-dimensional subspaces. As a result, the curse of dimensionality is alleviated to a large degree without sacrificing optimality. We demonstrate our theoretical results through a 3D Dubins Car model and a 6D Acrobatic Quadrotor model.

Asynchronous event-based sensors present new challenges in basic robot vision problems like feature tracking. The few existing approaches rely on grouping events into models and computing optical flow after assigning future events to those models. Such a hard commitment in data association attenuates the optical flow quality and causes shorter flow tracks. In this paper, we introduce a novel soft data association modeled with probabilities. The association probabilities are computed in an intertwined EM scheme with the optical flow computation that maximizes the expectation (marginalization) over all associations. In addition, to enable longer tracks we compute the affine deformation with respect to the initial point and use the resulting residual as a measure of persistence. The computed optical flow enables a varying temporal integration different for every feature and sized inversely proportional to the length of the flow. We show results in egomotion and very fast vehicle sequences and we show the superiority over standard frame-based cameras.

Evaluation and testing are critical for the development of Automated Vehicles (AVs). Currently, companies test AVs on public roads, which is very time-consuming and inefficient. We proposed the Accelerated Evaluation concept which uses a modified statistics of the surrounding vehicles and the Importance Sampling theory to reduce the evaluation time by several orders of magnitude, while ensuring the final evaluation results are accurate. In this paper, we further extend this idea by using Piecewise Mixture Distribution models instead of Single Distribution models. We demonstrate this idea to evaluate vehicle safety in lane change scenarios. The behavior of the cut-in vehicles was modeled based on more than 400,000 naturalistic driving lane changes collected by the University of Michigan Safety Pilot Model Deployment Program. Simulation results confirm that the accuracy and efficiency of the Piecewise Mixture Distribution method are better than the single distribution.

Brain-Machine Interface (BMI) has emerged as a powerful tool for assisting disabled people and for augmenting human performance. Up so far, no studies have succeeded in the power augmentation for the multi-DOFs robot based on EEG signals, especially for the complex shoulder joint. In this work, we propose an electromyography (EMG) estimation method based on electroencephalography (EEG) signals to realize the power assistance. The positions of the electrodes where the motion information of shoulder joint is effectively and exactly extracted are discussed, and a linear model that correlates the EMG to the EEG signal is constructed utilizing motion-related features extracted from multi-location EEG measurements. The constructed model is used to estimate the human muscular activity of shoulder joint from EEG using Principal Component Analysis (PCA) method. The proposed approach is experimentally verified, and an average correlation coefficients are as high as about 0.90 for different subjects are obtained between the estimated and the actually measured EMG signal. Our results suggest that the estimation of EMG based on EEG is feasible. This demonstrates the potential of using EEG signals to support human activities via brain-machine interface.

Knowing accurately the dynamic parameters of a manipulated object is required for common coordination strategies in physical human-robot interaction. Bias in object dynamics results in inaccurately calculated robot wrenches, which may disturb the human during interaction and bias the recognition of the human motion intention. This paper presents an identification strategy of object dynamics for physical human-robot interaction, which allows the tracking of desired human motion and inducing the motions necessary for parameter identification. The estimation of object dynamics is performed online and the estimator minimizes the least square error between the measured and estimated wrenches acting on the object. Identification-relevant motions are derived by analyzing the persistence of excitation condition, necessary for estimation convergence. Such motions are projected in the null space of the partial grasp matrix, relating the human and the robot redundant motion directions, to avoid disturbance of the human desired motion. The approach is evaluated in a physical human-robot object manipulation scenario.