ICRA 2022 论文列表

Physicians perform minimally invasive percuta-neous procedures under Computed Tomography (CT) image guidance both for the diagnosis and treatment of numerous diseases. For these procedures performed within Computed Tomography Scanners, robots can enable physicians to more accurately target sub-dermal lesions while increasing safety. However, existing robots for this application have limited dexterity, workspace, or accuracy. This paper describes the design, manufacture, and performance of a highly dexterous, low-profile, 8+2 Degree-of-Freedom (DoF) robotic arm for CT guided percutaneous needle biopsy. In this article, we propose CRANE: CT Robot and Needle Emplacer. The design focuses on system dexterity with high accuracy: extending physicians' ability to manipulate and insert needles within the scanner bore while providing the high accuracy possible with a robot. We also propose and validate a system architecture and control scheme for low profile and highly accurate image-guided robotics, that meets the clinical requirements for target accuracy during an in-situ evaluation. The accuracy is additionally evaluated through a trajectory tracking evaluation resulting in < \boldsymbol{0.2}\mathbf{mm}< \boldsymbol{0.2}\mathbf{mm} and <\boldsymbol{ 0.71}^{\circ}<\boldsymbol{ 0.71}^{\circ} tracking error. Finally, we present a novel needle driving and grasping mechanism with controlling electronics that provides simple manufacturing, sterilization, and adaptability to accom-modate different sizes and types of needles.

LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms. Previous point-based or sparse voxel-based methods are far away from real-time applications since time-consuming neighbor searching or sparse 3D convolution are employed. Recent 2D projection-based methods, including range view and multi-view fusion, can run in real time, but suffer from lower accuracy due to information loss during the 2 DD projection. Besides, to improve the performance, previous methods usually adopt test time augmentation (TTA), which further slows down the inference process. To achieve a better speed-accuracy trade-off, we propose Cascade Point-Grid Fusion Network (CPGNet), which ensures both effectiveness and efficiency mainly by the following two techniques: 1) the novel Point-Grid (PG) fusion block extracts semantic features mainly on the 2D projected grid for efficiency, while summarizes both 2D and 3D features on 3D point for minimal information loss; 2) the proposed transformation consistency loss narrows the gap between the single-time model inference and TTA. The experiments on the SemanticKITTI and nuScenes benchmarks demonstrate that the CPGNet without ensemble models or TTA is comparable with the state-of-the-art RPVNet, while it runs 4.7 times faster.

In this research, we aim to answer the question: How to combine Closed-Loop State and Input Sensitivity-based with Observability-aware trajectory planning? These possibly op-posite optimization objectives can be used to improve trajectory control tracking and, at the same time, estimation performance. Our proposed novel Control & Observability-aware Planning (COP) framework is the first that uses these possibly opposing objectives in a Single-Objective Optimization Problem (SOOP) based on the Augmented Weighted Tchebycheff method to perform the balancing of them and generation of Bézier curve-based trajectories. Statistically relevant simulations for a 3D quadrotor unmanned aerial vehicle (UAV) case study produce results that support our claims and show the negative correlation between both objectives. We were able to reduce the positional mean integral error norm as well as the estimation uncertainty with the same trajectory to comparable levels of the trajectories optimized with individual objectives.

We propose CLA-NeRF - a Category-Level Articulated Neural Radiance Field that can perform view synthesis, part segmentation, and articulated pose estimation. CLA-NeRF is trained at the object category level using no CAD models and no depth, but a set of RGB images with ground truth camera poses and part segments. During inference, it only takes a few RGB views (i.e., few-shot) of an unseen 3D object instance within the known category to infer the object part segmentation and the neural radiance field. Given an articulated pose as input, CLA-NeRF can perform articulation-aware volume rendering to generate the corresponding RGB image at any camera pose. Moreover, the articulated pose of an object can be estimated via inverse rendering. In our experiments, we evaluate the framework across five categories on both synthetic and real-world data. In all cases, our method shows realistic deformation results and accurate articulated pose estimation. We believe that both few-shot articulated object rendering and articulated pose estimation open doors for robots to perceive and interact with unseen articulated objects.

This paper presents CCRobot-V, the fifth version of CCRobot, a cooperative serial multi-robot system for bridge cable inspection and maintenance that uses silkworm-like locomotion to climb the entire length of super-long stay cable at high speeds while carrying heavy inspection/maintenance equipment. CCRobot-V consists of one climbing precursor robot, one inspection/maintenance robot, several cable-carrying robots, and a power-tethered cable guiding system. The pre-cursor robot is the “head,” which leads the affiliated sub-robots along the bridge cable. Every sub-robot possesses a pair of self-locking palms. When a sub-robot grips on the bridge cable with its palms, it becomes a fixed anchor point that allows the adjacent sub-robots in front and back to use winches and steel wires to pull themselves upward. With this cooperative multi-robot system, cable inspection/maintenance tasks can be divided into several functional units, with each inspection/maintenance equipment installed separately on a customized sub-robot. Thus, CCRobot-V provides a complete mobile inspection/maintenance work line for a bridge cable. The experimental and field tests demonstrate CCRobot-V's high climbing speed, high payload capacity, and full-length cable moving capability. It has the potential application value for the actual bridge cable inspection/maintenance.

We present CCO-VOXEL: the very first chance-constrained optimization (CCO) algorithm that can compute trajectory plans with probabilistic safety guarantees in real-time directly on the voxel-grid representation of the world. CCO-VOXEL maps the distribution over the distance to the closest obstacle to a distribution over collision-constraint violation and computes an optimal trajectory that minimizes the violation probability. Importantly, unlike existing works, we never assume the nature of the sensor uncertainty or the probability distribution of the resulting collision-constraint violations. We leverage the notion of Hilbert Space embedding of distributions and Maximum Mean Discrepancy (MMD) to compute a tractable surrogate for the original chance-constrained optimization problem and employ a combination of A* based graph-search and Cross-Entropy Method for obtaining its minimum. We show tangible performance gain in terms of collision avoidance and trajectory smoothness as a consequence of our probabilistic formulation vis a vis state-of-the-art planning methods that do not account for such non-parametric noise. Finally, we also show how a combination of low-dimensional feature embedding and pre-caching of Kernel Matrices of MMD allow us to achieve real-time performance in simulations as well as in implementations on on-board commodity hardware that controls the quadrotor flight.

From robotic space assistance to healthcare robotics, there is increasing interest in robots that offer adaptable levels of autonomy. In this paper, we propose an action representation and planning framework that is able to generate plans that can be executed with both shared control and supervised autonomy, even switching between them during task execution. The action representation - Constraint Action Templates (CATs) - combine the advantages of Action Templates [1] and Shared Control Templates [2]. We demonstrate that CATs enable our planning framework to generate goal-directed plans for variations of a typical task of daily living, and that users can execute them on the wheelchair-robot EDAN in shared control or in autonomous mode.

This paper presents an intelligent machine which can automatically convert the captured portrait into a physical gadget made up of LEGO bricks. On the contrary to synthesising a 2D image or a virtual 3D object, generating physical 3D assembly object needs to take physical properties and assembly process into consideration, leading to more challenges. To generate brick models for arbitrary portraits, we formulate the transformation between the attribute space (extracted from 2D images) and the brick model space as a constraint integer programming problem which can be solved with a heuristic search method. Furthermore, as the bricks are physically scattered, we propose an algorithm to generate corresponding assembly instructions for customized figure-featured-bricks to facilitate users' assembly. Meanwhile, we deploy the proposed algorithms on an automatic machine which integrates a camera, a printer, a laptop, and a brick operation unit. Finally, the generated brick models and assembly instructions are evaluated by a large number of users. It is worth noting that the whole system works as an intelligent vending machine, producing a 150-brick-model within 3 minutes.

Movement primitives have the property to accom-modate changes in the robot state while maintaining attraction to the original policy. As such, we investigate the use of primitives as a blending mechanism by considering that state deviations from the original policy are caused by user inputs. As the primitive recovers from the user input, it implicitly blends human and robot policies without requiring their weightings-referred to as arbitration. In this paper, we adopt Dynamical Movement Primitives (DMPs), which allow us to avoid the need for multiple demonstrations, and are fast enough to enable numerous instantiations, one for each hypothesis of the human intent. User studies are presented on assisted teleoperation tasks of reaching multiple goals and dynamic obstacle avoidance. Comparable performance to conventional teleoperation was achieved while significantly decreasing human intervention, often by more than 60%.

This paper presents an online walking synthesis methodology to enable dynamic and stable walking on constrained footholds for underactuated bipedal robots. Our approach modulates the change of angular momentum about the foot-ground contact pivot at discrete impact using pre-impact vertical center of mass (COM) velocity. To this end, we utilize the underactuated Linear Inverted Pendulum (LIP) model for approximating the underactuated walking dynamics to provide the desired post-impact angular momentum for each step. Desired outputs are constructed via online optimization combined with closed-form polynomials and tracked via a quadratic program (QP) based controller. This method is demonstrated on two robots, AMBER and 3D Cassie, for which stable walking behaviors with constrained footholds are realized on flat ground, stairs, and randomly located stepping stones.

Heart rhythm disorders are becoming increasingly prevalent with population aging. Atrial fibrillation ablation (AFA) is a procedure used to treat an irregular heart rhythm (arrhythmia) that starts in the heart's upper chambers. The AFA works by scarring or destroying heart tissue to disrupt aberrant conduction pathways causing the arrhythmia. In hospital cardiac units, a flexible catheter with integrated metal electrode is currently used for the AFA procedure. Despite advances, existing cardiac catheter tips are driven by cable mechanisms which are associated with high nonlinear hysteresis and force loss. In addition, they are also limited to rigid components which require multiple actuators to control the bending tip to reach the complex anatomical corners of the heart. This paper introduces a new soft hydraulic catheter that can achieve bidirectional bending motion via a single soft artificial muscle. The new catheter is also equipped with a portable handle as an ergonomic control interface. To validate the design concept, various prototypes are fabricated and tested including bending angles and generated force capability. Mathematical models for the bending arm are also developed and experimentally validated. The new soft catheter will enable rapid and precise manipulation to reach any target within the cardiac chambers, offering more rapid and focused ablation therapy to improve patient outcomes.

A fruitful collaboration is based on the mutual knowledge of each other skills and on the possibility of communicating their own limits and proposing alternatives to adapt the execution of a task to the capabilities of the collaborators. This paper aims at reproducing such a scenario in a human-robot collaboration setting by proposing a novel communication control architecture. Exploiting control barrier functions, the robot is made aware of its (dynamic) skills and limits and, thanks to a local predictor, it is able to assess if it is possible to execute a requested task and, if not, to propose alternative by relaxing some constraints. The controller is interfaced with a communication infrastructure that enables human and robot to set up a bidirectional communication about the task to execute and the human to take an informed decision on the behavior of the robot. A comparative experimental validation is proposed.

A new belief space planning algorithm, called covariance steering Belief RoadMap (CS-BRM), is introduced, which is a multi-query algorithm for motion planning of dynamical systems under simultaneous motion and observation uncertainties. CS-BRM extends the probabilistic roadmap (PRM) approach to belief spaces and is based on the recently developed theory of covariance steering (CS) that enables guaranteed satisfaction of terminal belief constraints in finitetime. The CS-BRM algorithm allows the sampling of non-stationary belief nodes, and thus is able to explore the velocity space and find efficient motion plans. We evaluate CS-BRM in different planning problems and demonstrate the benefits of the proposed approach.

In this paper, we propose a multi-domain control parameter learning framework that combines Bayesian Optimization (BO) and Hybrid Zero Dynamics (HZD) for locomotion control of bipedal robots. We leverage BO to learn the control parameters used in the HZD-based controller. The learning process is firstly deployed in simulation to optimize different control parameters for a large repertoire of gaits. Next, to tackle the discrepancy between the simulation and the real world, the learning process is applied on the physical robot to learn for corrections to the control parameters learned in simulation while also respecting a safety constraint for gait stability. This method empowers an efficient sim-to-real transition with a small number of samples in the real world, and does not require a valid controller to initialize the training in simulation. Our proposed learning framework is experimentally deployed and validated on a bipedal robot Cassie to perform versatile locomotion skills with improved performance on smoothness of walking gaits and reduction of steady-state tracking errors.

We propose an adaptive optimisation approach for tuning stochastic model predictive control (MPC) hyper-parameters while jointly estimating probability distributions of the transition model parameters based on performance rewards. In particular, we develop a Bayesian optimisation (BO) algorithm with a heteroscedastic noise model to deal with varying noise across the MPC hyper-parameter and dynamics model parameter spaces. Typical homoscedastic noise models are unrealistic for tuning MPC since stochastic controllers are inherently noisy, and the level of noise is affected by their hyper-parameter settings. We evaluate the proposed optimisation algorithm in simulated control and robotics tasks where we jointly infer control and dynamics parameters. Experimental results demonstrate that our approach leads to higher cumulative rewards and more stable controllers.

Distributed model predictive control (DMPC) concerns how to online control multiple robotic systems with constraints effectively. However, the nonlinearity, nonconvexity, and strong interconnections of dynamic system models and constraints can make the real-time and real-world DMPC implementations nontrivial. Reinforcement learning (RL) algorithms are promising for control policy design. However, how to ensure safety in terms of state constraints in RL remains a significant issue. This paper proposes a barrier function-based safe reinforcement learning algorithm for DMPC of nonlinear multi-robot systems under state constraints. The proposed approach is composed of several local learning-based MPC regulators. Each regulator, associated with a local system, learns and deploys the local control policy using a safe reinforcement learning algorithm in a distributed manner, i.e., with state information only among the neighbor agents. As a prominent feature of the proposed algorithm, we present a novel barrier-based policy structure to ensure safety, which has a clear mechanistic interpretation. Both simulated and real-world experiments on the formation control of mobile robots with collision avoidance show the effectiveness of the proposed safe reinforcement learning algorithm for DMPC.

In this work, we carry out structural and al-gorithmic studies of a problem of barrier forming: selecting the minimum number of straight line segments (barriers) that separate several sets of mutually disjoint objects in the plane. The problem models the optimal placement of line sensors (e.g., infrared laser beams) for isolating many types of regions in a pair- wise manner for practical purposes (e.g., guarding against intrusions). The problem is NP-hard even if we want to find the minimum number of lines to separate two sets of points in the plane. Under the umbrella problem of barrier forming with minimum number of line segments, three settings are examined: barrier forming for point sets, point sets with polygonal obstacles, polygonal sets with polygonal obstacles. We describe methods for computing the optimal solution for the first two settings with the assistance of mathematical programming, and provide a 2-OPT solution for the third. We demonstrate the effectiveness of our methods through extensive simulations.

Ultrasound beam propulsion, a propulsion system that uses airborne ultrasound phased arrays (AUPAs) to propel a blimp in an indoor environment to propel a blimp, has advantages for operations near humans such as no audible noises and no risk of propeller strike. To achieve the high mobility with limited actuation force of AUPAs, the dynamics should be fully exploited. In this paper, we propose a two-degree-of-freedom controller specifically tailored for ultrasound beam propulsion. We investigate the trajectory of bang-bang control with constant thrust (BBCT control), where a blimp accelerates and then decelerates with constant thrust reaching the terminal point at rest, as one of the most basic trajectories. First, we analytically derive the trajectory of a blimp under aerodynamic drag. Then, we provide a trajectory generator that derives the maximum constant thrust for an arrangement of AUPAs and the constraints on the control input. Finally, we integrate the trajectory generator and a PID-based feedback controller in a physical setup. We evaluated the proposed controller in physical and numerical experiments. The results showed that the proposed method allows a blimp to reach the terminal point almost in expected time. We also showed that the flight time is shorter than a PID-based one-degree-of-freedom controller, which was typically used in previous studies, by 19.0 − 43.2 %.

Robot-assisted feeding in household environments is challenging because it requires robots to generate trajectories that effectively bring food items of varying shapes and sizes into the mouth while making sure the user is comfortable. Our key insight is that in order to solve this challenge, robots must balance the efficiency of feeding a food item with the comfort of each individual bite. We formalize comfort and efficiency as heuristics to incorporate in motion planning. We present an approach based on heuristics-guided bi-directional Rapidly-exploring Random Trees (h-BiRRT) that selects bite transfer trajectories of arbitrary food item geometries and shapes using our developed bite efficiency and comfort heuristics and a learned constraint model. Real-robot evaluations show that op-timizing both comfort and efficiency significantly outperforms a fixed-pose based method, and users preferred our method significantly more than that of a method that maximizes only user comfort. Videos and Appendices are found on our website: https://tinyurl.com/bticra22.