ICRA 2020 Papers

This paper describes a distributed algorithm for computing the number of robots in a swarm, only requiring communication with neighboring robots. The algorithm can adjust the estimated count when the number of robots in the swarm changes, such as the addition or removal of robots. Probabilistic guarantees are given, which show the accuracy of this method, and the trade-off between accuracy, speed, and adaptability to changing numbers. The proposed approach is demonstrated in simulation as well as a real swarm of robots.

Estimating pose from given 3D correspondences, including point-to-point, point-to-line and point-to-plane correspondences, is a fundamental task in computer vision with many applications. We present a fast and accurate solution for the least-squares problem of this task. Previous works mainly focus on studying the way to find the global minimizer of the least-squares problem. However, existing works that show the ability to achieve the global minimizer are still unsuitable for real-time applications. Furthermore, as one of contributions of this paper, we prove that there exist ambiguous configurations for any number of lines and planes. These configurations have several solutions in theory, which makes the correct solution may come from a local minimizer when the data are with noise. Previous works based on convex optimization which is unable to find local minimizers do not work in the ambiguous configuration. Our algorithm is efficient and able to reveal local minimizers. We employ the Cayley-Gibbs-Rodriguez (CGR) parameterization of the rotation to derive a general rational cost for the three cases of 3D correspondences. The main contribution of this paper is to solve the first-order optimality conditions of the least-squares problem, which are of a complicated rational form. The central idea of our algorithm is to introduce some intermediate unknowns to simplify the problem. Extensive experimental results show that our algorithm is more stable than previous algorithms when the number N of correspondences is small. Besides, when N is large, our algorithm achieves the same accuracy as the state-of-the-art algorithm [1], but our algorithm is about 7 times faster than [1] in real applications.

We present a novel fast marching gradient sampling strategy to accelerate the convergence speed of sampling-based motion planning algorithms. This strategy is based on an informed certificate set which consists of the robot states with exact collision status as well as the minimum distance and the gradient to the nearest obstacle. The informed certificate set covers almost the whole planning space such that it contains rich information for the planner. The best quality point in this set is selected as the marching seed to guide the search graph move steadily to the goal set. The distance and gradient information of the marching seed helps to generate a new sample with almost sure collision status. When a feasible solution has been found, this set can construct the restricted subset that can improve current path quality. This marching gradient sampling strategy is applied to the RRT and RRT* algorithms. Simulation experiments demonstrate that the convergence speed to a feasible solution or to the optimal solution is almost twice faster than that of the safety certificate algorithms.

The Variable Topology Truss (VTT) is a new class of self-reconfigurable robot that can reconfigure its truss shape and topology depending on the task or environment requirements. Motion planning and avoiding self-collision are difficult as these systems usually have dozens of degrees-of-freedom with complex intersecting parallel actuation. There are two different types of shape changing actions for a VTT: geometry reconfiguration and topology reconfiguration. This paper focuses on the geometry reconfiguration actions. A new cell decomposition approach is presented based on a fast and complete method to compute the collision-free space of a node in a truss. A simple shape-morphing method is shown to quickly create motion paths for reconfiguration by moving one node at a time.

We present an integrated approach that provides compliant control of an iCub humanoid robot and adaptive reaching, grasping, navigating and co-manipulating capabilities. We use state-dependent dynamical systems (DS) to (i) coordinate and drive the robots hands (in both position and orientation) to grasp an object using an intermediate virtual object, and (ii) drive the robot's base while walking/navigating. The use of DS as motion generators allows us to adapt smoothly as the object moves and to re-plan on-line motion of the arms and body to reach the object's new location. The desired motion generated by the DS are used in combination with a whole-body compliant control strategy that absorbs perturbations while walking and offers compliant behaviors for grasping and manipulation tasks. Further, the desired dynamics for the arm and body can be learned from demonstrations. By integrating these components, we achieve unprecedented adaptive behaviors for whole body manipulation. We showcase this in simulations and real-world experiments where iCub robots (i) walk-to-grasp objects, (ii) follow a human (or another iCub) through interaction and (iii) learn to navigate or comanipulate an object from human guided demonstrations; whilst being robust to changing targets and perturbations.

The performance of model-based motion control for free-flying robots relies on accurate estimation of their parameters. In this work, a method of rigid body inertial parameter estimation which relies on a variational approach is presented. Instead of discretizing the continuous equations of motion, discrete dual quaternion equations based on variational mechanics are used to formulate a linear parameter estimation problem. This method depends only on the pose of the rigid body obtained from standard localization algorithms. Recursive semi-definite programming is used to estimate the inertial parameters (mass, rotational inertia and center of mass offset) online. Linear Matrix Inequality constraints based on the pseudo-inertia matrix ensure that the estimates obtained are fully physically consistent. Simulation results demonstrate that this method is robust to disturbances and the produced estimates are at least one order of magnitude more accurate when compared to discretization using finite differences.

High-end laser range-finders provide accurate 3D data over long ranges. But their scans are inhomogeneous, i.e., the environment is non-uniformly sampled, as there is denser data in the near range than in the far range. Furthermore, the generation of a scan is time-consuming. Thus, it is desirable to cover an area by as few scans as possible, i.e., scanning is more time-efficient if the overlap between scans is as small as possible. However, these factors pose significant challenges for state-of-the-art registration algorithms. In this work, we present a divide-and-conquer method that uses an efficient strategy to check for possible registrations between partitions of two scans. As underlying registration method, Fourier-Mellin-SOFT (FMS) is used. FMS is quite robust against partial overlaps but its performance is significantly boosted by the presented partitioning method. As concrete use case, results from the digitization of a WWII submarine bunker as a large-scale cultural heritage site are presented.

Finding sources of airborne chemicals with mobile sensing systems finds applications in safety, security, and emergency situations related to medical, domestic, and environmental domains. Given the often critical nature of all the applications, it is important to reduce the amount of time necessary to accomplish this task through intelligent systems and algorithms. In this paper, we extend a previously presented algorithm based on source term estimation for odor source localization for homogeneous multi-robot systems. By gradually increasing the level of coordination among multiple mobile robots, we study the benefits of a distributed system on reducing the amount of time and resources necessary to achieve the task at hand. The method has been evaluated systematically through high-fidelity simulations and in a wind tunnel emulating realistic and repeatable conditions in different coordination scenarios and with different number of robots.

Soft, tip-extending "vine" robots offer a unique mode of inspection and manipulation in highly constrained environments. For practicality, it is desirable that the distal end of the robot can be manipulated freely, while the body remains stationary. However, in previous vine robots, either the shape of the body was fixed after growth with no ability to manipulate the distal end, or the whole body moved together with the tip. Here, we present a concept for shape-locking that enables a vine robot to move only its distal tip, while the body is locked in place. This is achieved using two inextensible, pressurized, tip-extending, chambers that "grow" along the sides of the robot body, preserving curvature in the section where they have been deployed. The length of the locked and free sections can be varied by controlling the extension and retraction of these chambers. We present models describing this shape-locking mechanism and workspace of the robot in both free and constrained environments. We experimentally validate these models, showing an increased dexterous workspace compared to previous vine robots. Our shape-locking concept allows improved performance for vine robots, advancing the field of soft robotics for inspection and manipulation in highly constrained environments.

Painting textures on 3D surfaces requires an understanding of the surface geometry, paint flow and paint mixing. This work formulates automated painting as a planning problem and proposes a solution based on a self-supervised learning framework that enables a robot to paint monochromatic non-uniform textures on 3D surfaces. We developed a method that iteratively decides the actions to take based on constant feedback of the painting process. Inspired by recent results, we formulate our solution using a recurrent neural network (RNN) to decide where and what to paint on the surface at each time instant. Specifically, the paint delivery tool's flow rate, orientation and position relative to the surface at each time instant are evaluated. This data can then be processed by a robot's planner of choice for generating a painting mission that can achieve the desired end result. We evaluate the proposed approach by providing qualitative and quantitative results of the different components. Furthermore, we validate the effectiveness of the approach for the application by providing renderings from a paint simulation environment and show how a robot executes the planned painting mission on a generic 3D surface.

Within the Industry 4.0 context, industrial robots need to show increasing autonomy. The manipulator has to be able to react to uncertainties/changes in the working environment, displaying a robust behavior. In this paper, a control framework is proposed to perform industrial interaction tasks in uncertain working scenes. The proposed methodology relies on two components: i) a 6D pose estimation algorithm aiming to recognize large and featureless parts; ii) a variable damping impedance controller (inner loop) enhanced by an adaptive saturation PI (outer loop) for high accuracy force control (i.e., zero steady-state force error and force overshoots avoidance). The proposed methodology allows to be robust w.r.t. task uncertainties (i.e. , positioning errors and interaction dynamics). The proposed approach has been evaluated in an assembly task of a side-wall panel to be installed inside the aircraft cabin. As a test platform, the KUKA iiwa 14 R820 has been used together with the Microsoft Kinect 2.0 as RGB-D sensor. Experiments show the reliability in the 6D pose estimation and the high-performance in the force-tracking task, avoiding force overshoots while achieving the tracking of the reference force.

Continuum manipulators can accomplish various tasks in confined spaces, benefiting from their compliant structures and improved dexterity. Confined and unstructured spaces may require both enhanced stiffness of a continuum manipulator for precision and payload, as well as compliance for safe interaction. Thus, studies have been consistently dedicated to design continuum or articulated manipulators with tunable stiffness to adapt to different operating conditions. This paper presents a continuum manipulator with independently tunable stiffness where the stiffness variation does not affect the movement of the manipulator's end-effector. Moreover, the proposed continuum manipulator is found to have analytical inverse kinematics. The design concept, analytical kinematics, system construction and experimental characterizations are presented. The results showed that the manipulator's stiffness can be increased up to 3.61 times of the minimal value, demonstrating the effectiveness of the proposed idea.

This paper presents a method for predicting the probability of future connectivity between mobile robots with range-limited communication. In particular, we focus on its application to active motion planning for cooperative localization (CL). The probability of connection is modeled by the distribution of quadratic forms in random normal variables and is computed by the infinite power series expansion theorem. A finite-term approximation is made to realize the computational feasibility and three more modifications are designed to handle the adverse impacts introduced by the omission of the higher order series terms. On the basis of this algorithm, an active and CL problem with leader-follower architecture is then reformulated into a Markov Decision Process (MDP) with a one-step planning horizon, and the optimal motion strategy is generated by minimizing the expected cost of the MDP. Extensive simulations and comparisons are presented to show the effectiveness and efficiency of both the proposed prediction algorithm and the MDP model.

The supercoiled polymer (SCP) actuator is a novel artificial muscle, which is manufactured by twisting and coiling polymer fibers. This new artificial muscle is soft, low-cost and shows good linearity. Being utilized as an actuator, the artificial muscle could generate significant mechanical power in a muscle-like form upon electrical activation by Joule heating. In this study, we adopt this new artificial muscle to actuate a novel designed robotic manipulator, which is composed of two parts. The first part is a robotic arm based on the inspiration of the musculoskeletal system. The arm is fabricated with two ball-and-socket joints as skeleton and SCP actuators as driven muscles. The second part is a Fin Ray Effect inspired soft gripper that can perform grasping tasks on fragile objects. The manipulator prototype is fabricated and experimental tests are conducted including both simple but effective control of the bio-inspired arm as well as characterization of the gripper. Lastly, a pick and place demonstration of a fragile fruit is performed utilizing the proposed manipulator. We envision that the bio-inspired robotic manipulator design driven by SCP actuators could potentially be used in other robotic applications.

The present paper introduces a novel methodology for Unscented Kalman Filtering (UKF) on manifolds that extends previous work by the authors on UKF on Lie groups. Beyond filtering performance, the main interests of the approach are its versatility, as the method applies to numerous state estimation problems, and its simplicity of implementation for practitioners not being necessarily familiar with manifolds and Lie groups. We have developed the method on two independent open-source Python and Matlab frameworks we call UKF-M, for quickly implementing and testing the approach. The online repositories contain tutorials, documentation, and various relevant robotics examples that the user can readily reproduce and then adapt, for fast prototyping and benchmarking. The code is available at https://github.com/CAOR-MINES-ParisTech/ukfm.

The problem of human-exoskeleton interaction with uncertain dynamical parameters remains an open-ended research area. It requires an elaborate control strategy design of the exoskeleton to accommodate complex and unpredictable human body movements. In this paper, we proposed a novel control approach for the lower limb exoskeleton to realize its task of assisting the human operator walking. The main challenge of this study was to determine the human lower extremity dynamics, such as the joint torque. For this purpose, we developed a neural network-based torque estimation method. It can predict the joint torques of humans with surface electromyogram signals (sEMG). Then an radial basis function neural network (RBF NN) enhanced adaptive impedance controller is employed to ensure exoskeleton track desired motion trajectory of a human operator. Algorithm performance is evaluated with two healthy subjects and the rehabilitation lower-limb exoskeleton developed by Shenzhen Institutes of Advanced Technology (SIAT).

Scalability is a significant challenge for robot swarms. Generally, larger groups of cooperating robots produce more inter-robot collisions, and in swarm robot foraging, larger search arenas result in larger travel costs. This paper demonstrates a scale-invariant swarm foraging algorithm that ensures that each robot finds and delivers targets to a central collection zone at the same rate regardless of the size of the swarm or the search area. Dispersed mobile depots aggregate locally collected targets and transport them to a central place via a hierarchical branching transportation network. This approach is inspired by ubiquitous fractal branching networks such as tree branches and animal cardiovascular networks that deliver resources to cells and determine the scale and pace of life. We demonstrate that biological scaling laws predict how quickly robots forage in simulations of up to thousands of robots searching over thousands of square meters. We then use biological scaling to predict the capacity of depot robots that overcome scaling constraints to produce scale-invariant robot swarms. We verify the claims for large swarms in simulation and implement a simple depot design in hardware.

THIS paper presents a bidirectional 3D-printed soft pneumatic actuator that is capable of inward and outward bending. A direct 3D-printing approach is adopted to fabricate the actuator, which reduces fabrication complexity and allows for easy customization of actuator dimensions for various applications. To illustrate the applicability of the bidirectional actuators, four of these actuators were incorporated into a gripper system. A suite of various functional grasping tasks, such as packaging, assembly, and alignment tasks, were successfully conducted. It was observed that the unique bidirectional bending characteristic of the actuator allows the gripper to grasp objects with sizes up to 245% larger than its default grasping width. To complement the gripper system, a graphite-based flex sensor that is able to sense bending in two directions is developed to control the bidirectional actuators. A preliminary test was conducted successfully where the user controlled the gripper system to grasp, hold, and release an object using a glove with the sensors.

Augmented Reality and mobile robots are gaining increased attention within industries due to the high potential to make processes cost and time efficient. To facilitate augmented reality, a calibration between the Augmented Reality device and the environment is necessary. This is a challenge when dealing with mobile robots due to the mobility of all entities making the environment dynamic. On this account, we propose a novel approach to calibrate Augmented Reality devices using 3D depth sensor data. We use the depth camera of a Head Mounted Augmented Reality Device, the Microsoft Hololens, for deep learning-based calibration. Therefore, we modified a neural network based on the recently published VoteNet architecture which works directly on raw point cloud input observed by the Hololens. We achieve satisfying results and eliminate external tools like markers, thus enabling a more intuitive and flexible work flow for Augmented Reality integration. The results are adaptable to work with all depth cameras and are promising for further research. Furthermore, we introduce an open source 3D point cloud labeling tool, which is to our knowledge the first open source tool for labeling raw point cloud data.