ICRA 2019 Papers

Low weight and innate compliance make soft pneumatic actuators an attractive method for actuating wearable robots. Performance of soft pneumatic actuators can be tailored to an application by combining them in novel architectures. We modeled and constructed nested linear and pennate architectures using fiber-reinforced elastomeric enclosures (FREEs) with identical manufacturing parameters and total effective lengths to compare their suitability for a cable-driven exoskeleton for augmenting shoulder flexion. We determined actuator performance requirements using a static model for the transmission of actuator forces to the upper arm via Bowden cables. We experimentally characterized the architectures by measuring their force-displacement curves at a range of pressures, yielding greater force and displacement from the nested architecture in the domain required by our exoskeleton. Results also indicated a force threshold above which the pennate structure produced greater force at any given displacement. We validated the nested linear architecture using a prototype exoskeleton installed on a passive mannequin. Measured joint angles at varying pressures were close to predicted values, adjusted for measured losses due to cable anchor movement.

This paper introduces Probabilistic Chekov (p-Chekov), a chance-constrained motion planning system that can be applied to high degree-of-freedom (DOF) robots under motion uncertainty and imperfect state information. Given process and observation noise models, it can find feasible trajectories which satisfy a user-specified bound over the probability of collision. Leveraging our previous work in deterministic motion planning which integrated trajectory optimization into a sparse roadmap framework, p-Chekov shows superiority in its planning speed for high-dimensional tasks. P-Chekov incorporates a linear-quadratic Gaussian motion planning approach into the estimation of the robot state probability distribution, applies quadrature theories to waypoint collision risk estimation, and adapts risk allocation approaches to assign allowable probabilities of failure among waypoints. Unlike other existing risk-aware planners, p-Chekov can be applied to high-DOF robotic planning tasks without the convexification of the environment. The experiment results in this paper show that this p-Chekov system can effectively reduce collision risk and satisfy user-specified chance constraints in typical real-world planning scenarios for high-DOF robots.

Physical simulators have been widely used in robot planning and control. Among them, differentiable simulators are particularly favored, as they can be incorporated into gradient-based optimization algorithms that are efficient in solving inverse problems such as optimal control and motion planning. Therefore, rigid body simulators and recently their differentiable variants are studied extensively. Simulating deformable objects is, however, more challenging compared to rigid body dynamics. The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and there-fore they are significantly more computationally expensive to simulate. Computing gradients with respect to physical design or controller parameters is typically even more computationally challenging. In this paper, we propose a real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM). MLS-MPM can simulate deformable objects with collisions and can be seamlessly incorporated into soft robotic systems. We demonstrate that our simulator achieves high precision in both forward simulation and backward gradient computation. We have successfully employed it in a diverse set of inference, control and co-design tasks for soft robotics.

We introduce the concept of Momentum Driven Structures (MDS) made of inertially actuated units linked together by compliant elements as a potential solution for rough environments exploration. We propose a control method for MDS based on the bio-inspired concept of Central Pattern Generator (CPG) and study in simulation the impact of compliance distribution on locomotion performance using population based optimization techniques. Our results suggest that compliant structures outperform their rigid counterparts in terms of distance traveled. In addition, we show that co-evolved structures perform only marginally better than their control-only optimized equivalent, highlighting the fact that compliance modulation may not be a significant asset in such experiments, considering the related hardware complexity it introduces.

We propose an innovative design of microrobot, which can achieve donor cell suction, delivery and injection in a mammalian oocyte on microfluidic chip. The microrobot body contains a hollow space that produces suction and ejection forces for injection of cell nuclei using a nozzle at the tip of the robot. Specifically, a controller changes the hollow volume by balancing the magnetic and elastic forces of the membrane, and along with motion of stages in the XY plane. A glass capillary attached at the tip of the robot contains the nozzle is able to absorb and inject cell nuclei. The microrobot provides three degrees of freedom and generates micronewton forces. We demonstrate the effectiveness of the proposed microrobot through an experiment of absorption and ejection of 20 μm particles from the nozzle using magnetic control in a microfluidic chip.

This work introduces a framework for the Cartesian control of multi-legged, highly redundant robots. The proposed framework allows the untrained user to perform complex motion tasks with robotics platforms by leveraging a simple, auto-generated ROS-based interface. Contrary to other motion control frameworks (e.g. ROS MoveIt!), we focus on the execution of Cartesian trajectories that are specified online, rather than planned in advance, as it is the case, for instance, in tele-operation and locomotion tasks. Moreover, we address the problem of generating such motions within a hard real-time (RT) control loop. Finally, we demonstrate the capabilities of our framework both on the COMAN + humanoid robot, and on the hybrid wheeled-legged quadruped CENTAURO.

In this paper, we introduce a cargo transportation method with a new type of multi-rotor UAV platform known as T3-multirotor, to achieve stable and constant flight performance regardless of the type of cargo attached to the fuselage. The T3-multirotor, which consists of the `Thrust Generating Part' and the `Fuselage Part', can directly control the relative attitude between the two parts using the novel servomechanism. By utilizing the servomechanism with the proposed relative attitude control strategy, the T3-multirotor with cargo attached to the fuselage part can behave as a multi-rotor with only the moment of inertia of the thrust generating part during entire transportation. This allows the T3-multirotor to achieve the reliable performance in the event of any cargo being attached to the fuselage, achieving stable platform motion control. Detailed hardware description and dynamic analysis of T3-Multirotor is performed in this paper, and the validity of the proposed control strategy is also analyzed. The feasibility of the proposed control strategy is verified through experimental results with analysis.

Capillary Ionic Transistor (CIT) is introduced as a nanodevice which provides control of ionic transport through nanochannel by gate voltage. CIT is Ionic transistor which employs pulled capillary as nanochannel with tip diameter smaller than 100 nm. We observed that gate voltage applied to gate electrode, deposited on the outer wall of capillary, affect a conductance of nanochannel, due to change of surface charge at the solution/capillary interface. Negative gate voltage corresponds to lower conductivity and positive gate increase conductance of the channel. This effect strongly depends on the size of the channel. In general, at least one dimension of the channel has to be small enough for electrical double layer to overlap. As a demonstration of the gate control ability, we performed Si nanoparticle delivery via CIT and recorded the deliverance through resistive pulse method. Size and velocity measurement are also conducted, to showcase the versatility of CIT device.

Multi-robot systems are deployed in a warehouse to automate the process of storing and retrieving objects in and out of the warehouse. The efficiency of the system largely depends on how the tasks are allocated to the robots. Though there exists a number of techniques that can perform multi-robot task allocation quite efficiently, they hardly consider deadline for task completion while assigning tasks to the robots. A careful allocation is of paramount importance when there is an associated penalty with each of the tasks if it is not completed within a stipulated time. In this work, we develop an algorithm, called Minimum Penalty Scheduling (MPS) that allocates tasks among a group of robots with the goal that the overall penalty of executing all the tasks can be minimized. Our algorithm provides a robust, scalable, and near-optimal real-time task schedule. By comparing with the state-of-the-art algorithm, we show that MPS attracts up to 62.5% less penalty when a significant number of tasks are bound to miss the deadline. Additionally, MPS is also suitable for real-time multi-processor scheduling since it schedules a higher number of tasks within their deadline.

Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms. In comparison with existing VO and V-SLAM algorithms, semi-direct visual odometry (SVO) has two main advantages that lead to state-of-the-art frame rate camera motion estimation: direct pixel correspondence and efficient implementation of probabilistic mapping method. This paper improves the SVO mapping by initializing the mean and the variance of the depth at a feature location according to the depth prediction from a single-image depth prediction network. By significantly reducing the depth uncertainty of the initialized map point (i.e., small variance centred about the depth prediction), the benefits are twofold: reliable feature correspondence between views and fast convergence to the true depth in order to create new map points. We evaluate our method with two outdoor datasets: KITTI dataset and Oxford Robotcar dataset. The experimental results indicate that improved SVO mapping results in increased robustness and camera tracking accuracy. The implementation of this work is available at https: //github.com/yan99033/CNN-SVO

This work presents a new contact-based 3D path planning approach for manipulators using robot skin. We make use of the Stochastic Functional Gradient Path Planner, extending it to the 3D case, and assess its usefulness in combination with multi-modal robot skin. Our proposed algorithm is verified on a 6 DOF robot arm that has been covered with multi-modal robot skin. The experimental platform is combined with a skin based compliant controller, making the robot inherently reactive. We implement different state-of-the-art planners within our contact-based robot system to compare their performance under the same conditions. In this way, all the planners use the same skin compliant control during evaluation. Furthermore, we extend the stochastic planner with tactile-based explorative behavior to improve its performance, especially for unknown environments. We show that CHiMP is able to outperform state of the art algorithms when working with skin-based sparse contact data.

The fusion of Iterative Closest Point (ICP) registrations in existing state estimation frameworks relies on an accurate estimation of their uncertainty. In this paper, we study the estimation of this uncertainty in the form of a covariance. First, we scrutinize the limitations of existing closed-form covariance estimation algorithms over 3D datasets. Then, we set out to estimate the covariance of ICP registrations through a data-driven approach, with over 5100000 registrations on 1020 pairs from real 3D point clouds. We assess our solution upon a wide spectrum of environments, ranging from structured to unstructured and indoor to outdoor. The capacity of our algorithm to predict covariances is accurately assessed, as well as the usefulness of these estimations for uncertainty estimation over trajectories. The proposed method estimates covariances better than existing closed-form solutions, and makes predictions that are consistent with observed trajectories.

Future robotic assembly systems will allow product designers to upload their assembled product models remotely such that they can be assembled autonomously. In this work we present the architecture for a Click and Assemble Robotic Assembly (CARA) system. This architecture takes an assembly file uploaded by the user through a web interface as the only input. It then performs all the necessary planning before executing the assembly. To the authors' knowledge, this is the first time that all of the required components from previous advances in robotic assembly have been brought together, with all interconnecting challenges solved, into a complete working system for physical, real world assembly tasks. To demonstrate the implemented architecture capabilities, a real industrial product with tight tolerances was assembled from its CAD file only, illustrating the end to end robotic assembly premise in a real world setting.

The SAE AutoDrive Challenge is a three-year competition to develop a Level 4 autonomous vehicle by 2020. The first set of challenges were held in April of 2018 in Yuma, Arizona. Our team (aUToronto/Zeus) placed first. In this paper, we describe Zeus' complete system architecture and specialized algorithms that enabled us to win. We show that it is possible to develop a vehicle with basic autonomy features in just six months relying on simple, robust algorithms. We do not make use of a prior map. Instead, we have developed a multi-sensor visual localization solution. All the algorithms in the paper run in real-time using CPUs only. We also highlight the closed-loop performance of the system in detail in several experiments.

In this work, we propose a novel paradigm to design a hybrid thermal/EO (Electro-Optical or visible-light) camera, whose thermal and RGB frames are pixel-wisely aligned and temporally synchronized. Compared with the existing schemes, we innovate in three ways in order to make it more compact in dimension, and thus more practical and extendable for real-world applications. The first is a redesign of the structure layout of the thermal and EO cameras. The second is on obtaining a pixel-wise spatial registration of the thermal and RGB frames by a coarse mechanical adjustment and a fine alignment through a constant homography warping. The third innovation is on extending one single hybrid camera to a hybrid camera array, through which we can obtain wide-view spatially aligned thermal, RGB and disparity images simultaneously. The experimental results show that the average error of spatial-alignment of two image modalities can be less than one pixel.

Safety analysis is a necessary component in the design and deployment of autonomous robotic systems. Techniques from robust optimal control theory, such as Hamilton-Jacobi reachability analysis, allow a rigorous formalization of safety as guaranteed constraint satisfaction. Unfortunately, the computational complexity of these tools for general dynamical systems scales poorly with state dimension, making existing tools impractical beyond small problems. Modern reinforcement learning methods have shown promising ability to find approximate yet proficient solutions to optimal control problems in complex and high-dimensional systems, however their application has in practice been restricted to problems with an additive payoff over time, unsuitable for reasoning about safety. In recent work, we introduced a time-discounted modification of the problem of maximizing the minimum payoff over time, central to safety analysis, through a modified dynamic programming equation that induces a contraction mapping. Here, we show how a similar contraction mapping can render reinforcement learning techniques amenable to quantitative safety analysis as tools to approximate the safe set and optimal safety policy. This opens a new avenue of research connecting control-theoretic safety analysis and the reinforcement learning domain. We validate the correctness of our formulation by comparing safety results computed through Q-learning to analytic and numerical solutions, and demonstrate its scalability by learning safe sets and control policies for simulated systems of up to 18 state dimensions using value learning and policy gradient techniques.

A robot making contact with an environment or human presents potential safety risks, including excessive collision force. While experiments on the effect of robot inertia, relative velocity, and interface stiffness on collision are in literature, analytical models for maximum collision force are limited to a simplified mass-spring robot model. This simplified model limits the analysis of control (force/torque, impedance, or admittance) or compliant robots (joint and end-effector compliance). Here, the Sobolev norm is adapted to be a system norm, giving rigorous bounds on the maximum force on a stiffness element in a general dynamic system, allowing the study of collision with more accurate models and feedback control. The Sobolev norm can be found through the H2 norm of a transformed system, allowing efficient computation, connection with existing control theory, and controller synthesis to minimize collision force. The Sobolev norm is validated, first experimentally with an admittance-controlled robot, then in simulation with a linear flexible-joint robot. It is then used to investigate the impact of control, joint flexibility and end-effector compliance on collision, and a trade-off between collision performance and environmental estimation uncertainty is shown.

The ability to interpret a scene is an important capability for a robot that is supposed to interact with its environment. The knowledge of what is in front of the robot is, for example, relevant for navigation, manipulation, or planning. Semantic segmentation labels each pixel of an image with a class label and thus provides a detailed semantic annotation of the surroundings to the robot. Convolutional neural networks (CNNs) are popular methods for addressing this type of problem. The available software for training and the integration of CNNs for real robots, however, is quite fragmented and often difficult to use for non-experts, despite the availability of several high-quality open-source frameworks for neural network implementation and training. In this paper, we propose a tool called Bonnet, which addresses this fragmentation problem by building a higher abstraction that is specific for the semantic segmentation task. It provides a modular approach to simplify the training of a semantic segmentation CNN independently of the used dataset and the intended task. Furthermore, we also address the deployment on a real robotic platform. Thus, we do not propose a new CNN approach in this paper. Instead, we provide a stable and easy-to-use tool to make this technology more approachable in the context of autonomous systems. In this sense, we aim at closing a gap between computer vision research and its use in robotics research. We provide an open-source codebase for training and deployment. The training interface is implemented in Python using TensorFlow and the deployment interface provides C++ library that can be easily integrated in an existing robotics codebase, a ROS node, and two standalone applications for label prediction in images and videos.

Much current study of legged locomotion has rightly focused on foot traction forces, including on granular media. Future legged millirobots will need to go through terrain, such as brush or other vegetation, where the body contact forces significantly affect locomotion. In this work, a (previously developed) low-cost 6-axis force/torque sensing shell is used to measure the interaction forces between a hexapedal millirobot and a set of compliant beams, which act as a surrogate for a densely cluttered environment. Experiments with a VelociRoACH robotic platform are used to measure lift and drag forces on the tactile shell, where negative lift forces can increase traction, even while drag forces increase. The drag energy and specific resistance required to pass through dense terrains can be measured. Furthermore, some contact between the robot and the compliant beams can lower specific resistance of locomotion. For small, light-weight legged robots in the beam environment, the body motion depends on both legground and body-beam forces. A shell-shape which reduces drag but increases negative lift, such as the half-ellipsoid used, is suggested to be advantageous for robot locomotion in this type of environment.