ICRA 2023 论文列表

This paper proposes Contour Context, a simple, effective, and efficient topological loop closure detection pipeline with accurate 3-DoF metric pose estimation, targeting the urban autonomous driving scenario. We interpret the Cartesian bird's eye view (BEV) image projected from 3D LiDAR points as layered distribution of structures. To recover elevation information from BEVs, we slice them at different heights, and connected pixels at each level form contours. Each contour is parameterized by abstract information, e.g., pixel count, center position, covariance, and mean height. The similarity of two BEVs is calculated in sequential discrete and continuous steps. The first step considers the geometric consensus of graph-like constellations formed by contours in particular localities. The second step models the majority of contours as a 2.5D Gaussian mixture model, which is used to calculate correlation and optimize relative transform in continuous space. A retrieval key is designed to accelerate the search of a database indexed by layered KD-trees. We validate the efficacy of our method by comparing it with recent works on public datasets.

In this paper, we propose a continuous-time-based LiDAR-inertial-vehicle odometry method, which can tightly fuse the data from Light Detection And Ranging (LiDAR), inertial measurement units (IMU), and vehicle measurements. The lateral acceleration constraint is further added to trajectory estimation to make the estimated trajectory follow the motion characteristics of vehicles. In addition, since vehicle model parameters vary with different motion conditions and tyre pressure, we estimate vehicle correction factors that rectify changes in vehicle model parameters online, and also analyze the observability of these vehicle correction factors. In experiments, the proposed method is evaluated and compared with state-of-the-art methods in the public dataset. The experimental results show that the proposed method achieves more accurate results in all sequences since we add additional sensor measurements and utilize the characteristic of vehicle motion to restrict the trajectory estimation. The ablation study also proved the effectiveness of continuous-time representation, online correction factor estimation, and incorporation of lateral acceleration constraint.

This work addresses the issue of motion compensation and pattern tracking in event camera data. An event camera generates asynchronous streams of events triggered independently by each of the pixels upon changes in the observed intensity. Providing great advantages in low-light and rapid-motion scenarios, such unconventional data present significant research challenges as traditional vision algorithms are not directly applicable to this sensing modality. The proposed method decomposes the tracking problem into a local SE(2) motion-compensation step followed by a homography registration of small motion-compensated event batches. The first component relies on Gaussian Process (GP) theory to model the continuous occupancy field of the events in the image plane and embed the camera trajectory in the covariance kernel function. In doing so, estimating the trajectory is done similarly to GP hyperparameter learning by maximising the log marginal likelihood of the data. The continuous occupancy fields are turned into distance fields and used as templates for homography-based registration. By benchmarking the proposed method against other state-of-the-art techniques, we show that our open-source implementation performs high-accuracy motion compensation and produces high-quality tracks in real-world scenarios.

Unlike traditional hierarchical controllers for robotic leg prostheses and exoskeletons, continuous systems could allow persons with mobility impairments to walk more naturally in real-world environments without requiring high-level switching between locomotion modes. To support these next-generation controllers, we developed a new system called KIFNet (Kinematics and Image Fusing Network) that uses lightweight and efficient deep learning models to continuously predict the leg kinematics during walking. We tested different sensor fusion methods to combine kinematics data from inertial sensors and computer vision data from smart glasses and found that adaptive instance normalization achieved the lowest RMSE predictions for knee and ankle joint kinematics. We also deployed our model on an embedded device. Without inference optimization, our model was 20 times faster than the previous state-of-the-art and achieved 20% higher prediction accuracies, and during some locomotor activities like stair descent, decreased RMSE up to 300%. With inference optimization, our best model achieved 125 FPS on an NVIDIA Jetson Nano. These results demonstrate the potential to build fast and accurate deep learning models for continuous prediction of leg kinematics during walking based on sensor fusion and embedded computing, therein providing a foundation for real-time continuous controllers for robotic leg prostheses and exoskeletons.

Unmanned aerial vehicle (UAV) tracking is crucial for autonomous navigation and has broad applications in robotic automation fields. However, reliable UAV tracking remains a challenging task due to various difficulties like frequent occlusion and aspect ratio change. Additionally, most of the existing work mainly focuses on explicit information to improve tracking performance, ignoring potential interframe connections. To address the above issues, this work proposes a novel framework with continuity-aware latent interframe information mining for reliable UAV tracking, i.e., ClimRT. Specifically, a new efficient continuity-aware latent interframe information mining network (ClimNet) is proposed for UAV tracking, which can generate highly-effective latent frame between two adjacent frames. Besides, a novel location-continuity Transformer (LCT) is designed to fully explore continuity-aware spatial-temporal information, thereby markedly enhancing UAV tracking. Extensive qualitative and quantitative experiments on three authoritative aerial benchmarks strongly validate the robustness and reliability of ClimRT in UAV tracking performance. Furthermore, real-world tests on the aerial platform validate its practicability and effectiveness. The code and demo materials are released at https://github.com/vision4robotics/ClimRT.

We consider the problem of task assignment and scheduling for human-robot teams to enable the efficient completion of complex problems, such as satellite assembly. In high-mix, low volume settings, we must enable the human-robot team to handle uncertainty due to changing task requirements, potential failures, and delays to maintain task completion efficiency. We make two contributions: (1) we account for the complex interaction of uncertainty that stems from the tasks and the agents using a multi-agent concurrent MDP framework, and (2) we use Mixed Integer Linear Programs and contingency sampling to approximate action values for task assignment. Our results show that our online algorithm is computationally efficient while making optimal task assignments compared to a value iteration baseline. We evaluate our method on a 24-task representative assembly and a real-world 60-task satellite assembly, and we show that we can find an assignment that results in a near-optimal makespan.

Many critical robot environments, such as healthcare and security, require robots to account for contextdependent criteria when performing their functions (e.g., navigation). Such domains require decisions that balance multiple factors, making it difficult for robots to make contextually appropriate decisions. Multi-Objective Optimization (MOO) methods offer a potential solution by trading off between objectives; however concepts like Pareto fronts are not only expensive to compute but struggle with differentiating among solutions on the Pareto front. This work introduces the Contextual Multi-Objective Path Planning (CMOPP) algorithm, which enables the robot to trade off different complex costs dependent on context. The key insight of this work is to separate the path planning and path cost estimation into two independent steps, thus significantly reducing computation cost without impacting the quality of the resulting path. As a result, CMOPP is able to accurately model path costs, which provide meaningful trade-offs when choosing a path that best fits the context. We show the benefits of CMOPP on case studies that demonstrate its contextual path planning capabilities. CMOPP finds contextually appropriate paths by first reducing the search space up to 99.9% to a near-optimal set of paths. This reduction enables the generation of accurate path cost models, using up to 90% less computation than similar methods.

Collaborative robots became a popular tool for increasing productivity in partly automated manufacturing plants. Intuitive robot teaching methods are required to quickly and flexibly adapt the robot programs to new tasks. Gestures have an essential role in human communication. However, in human-robot-interaction scenarios, gesture-based user interfaces are so far used rarely, and if they employ a one-to-one mapping of gestures to robot control variables. In this paper, we propose a method that infers the user's intent based on gesture episodes, the context of the situation, and common sense. The approach is evaluated in a simulated table-top manipulation setting. We conduct deterministic experiments with simulated users and show that the system can even handle the personal preferences of each user.

This paper presents a method for contact-based pose estimation of workpieces using a collaborative robot. The proposed pose estimation exploits positions and surface normal vectors along an arbitrary path on an object with known geometry, where surface normal vectors are estimated based on contact forces measured by the robot. When data is only available along a single path, it is difficult to find initial correspondences between source data (recorded points and normal vectors) and target data (CAD of an object); hence, a novel weighted incremental spatial search approach for generating correspondences based on point pair features is proposed. Subsequently, robust pose estimation is employed to reduce the effect of erroneous correspondences. The proposed pose estimation is verified in simulation on three paths on two objects and with different levels of noise on the source data to quantify the robustness of the algorithm. Finally, the method is experimentally validated to provide an average pose rotation and translation accuracy of \mathbf{0.55}^{\circ}\mathbf{0.55}^{\circ} and 0.51 mm, respectively, when using the robust estimation cost function Geman-McClure.

Recent studies on quadruped robots have focused on either locomotion or mobile manipulation using a robotic arm. However, legged robots can manipulate large objects using non-prehensile manipulation primitives, such as planar pushing, to drive the object to the desired location. This paper presents a novel hierarchical model predictive control (MPC) for contact optimization of the manipulation task. Using two cascading MPCs, we split the loco-manipulation problem into two parts: the first to optimize both contact force and contact location between the robot and the object, and the second to regulate the desired interaction force through the robot locomotion. Our method is successfully validated in both simulation and hardware experiments. While the baseline locomotion MPC fails to follow the desired trajectory of the object, our proposed approach can effectively control both object's position and orientation with minimal tracking error. This capability also allows us to perform obstacle avoidance for both the robot and the object during the loco-manipulation task.

This paper presents a novel robotic leg design and an associated control approach, which aims at providing an extension to the classical series elastic actuation concept. We propose to directly integrate the series compliance into the structure of the robotic leg itself, as opposed to co-locating spring and motor as done in traditional series elastic actuators. Our approach will eliminate mechanical design complexity and lead to a reduction of mass in the legs. This will, as a secondary benefit, improve the energy efficiency of locomotion. The primary contribution of this work is a model-based controller that can stably and precisely regulate the ground contact forces during stance. This control approach is demonstrated in a set of test-bench experiments, in which we control the contact forces of a modified version of the robotic leg ScarlETH. Here, the rigid shank is replaced by a continuously compliant element made of spring steel. This work presents the first step towards a new generation of robotic legs with structural compliance.

How does a wheeled robot move and turn? The answer is straightforward for a conventional wheeled robot, but it is not so easy for a robot with a discrete wheel design. Regular wheeled robots always have four contact points, resulting in static stability during locomotion. However, QuadRunner's novel leg mechanism provides only a semi-circular wheel shape, and proper gait planning is needed to go straight or turn. Therefore, this paper presents a dual frequency gait planning method which controls the robot's gait cycle's duty factor and generates unique turning gait patterns for wheel locomotion. Describing requirements and limitations, we found sets of solutions that can achieve turning. Results show that the smallest turning radius QuadRunner achieved is 1.05m, and the biggest is 1.86m. In addition, detailed experiments were made to observe the performance and stability of straight and turning wheel behaviors. Finally, a gait verification is made using high-speed cameras.

We propose a manifold optimization approach for solving constrained inference and planning problems. The approach employs a framework that transforms an arbitrary nonlinear equality constrained optimization problem into an unconstrained manifold optimization problem. The core of the transformation process is the formulation of constraint manifolds that represent sets of variables subject to equality constraints. We propose various approaches to define the tan-gent spaces and retraction operations of constraint manifolds, which are crucial for manifold optimization. We evaluate our constraint manifold optimization approach on multiple constrained inference and planning problems, and show that it generates strictly feasible results with increased efficiency as compared to state-of-the-art constrained optimization methods.

Cable-Driven Parallel Robots (CDPRs) are well-adapted to large workspaces since they replace rigid links by cables. However, they lack in positioning accuracy and new control methods are necessary to achieve profile-following tasks. This paper presents a control scheme designed for these tasks, relying on a combination of accurate boarded distance sensors and of a less accurate remote camera. The profile-following task is divided into two subtasks that are partially conflicting: maintaining a parallel orientation and a constant distance with the surface to follow, and following a trajectory between two points on the surface. The data fusion to solve the redundancy is based on the Gradient Projection Method. This control scheme is validated experimentally on a CDPR prototype and shown to provide the expected behaviour.

This paper introduces a deep learning (DL) approach to predicting congestion delays in large multi-robot systems. The problem is motivated by real-world problems in modern logistics automation, such as a warehouse with hundreds to thousands of coordinated mobile robots. Here, the large scale, the complexity of the control software, and the uncertainties of the robots' dynamics make direct (simulated) prediction of future robot states impractical. We propose predicting delays associated with future spatiotemporal locations, and we show this is useful for improving system performance via incorporating the predictions into path planning and travel time estimation. Our DL model uses convolutional long short-term memory (ConvLSTM) as the core structure, takes the historical congestion condition and planned paths as input, and generates the delays across all nodes in the spatial planning graph for a set of future time windows. When using predictions in a modified path planner, simulation experiments using production data show 4.4% average improvement in throughput performance versus without predictions.

Automated Valet Parking (AVP) has been exten-sively researched as an important application of autonomous driving. Considering the high dynamics and density of real parking lots, a system that considers multiple vehicles simultaneously is more robust and efficient than a single vehicle setting as in most studies. In this paper, we propose a dis-tributed Multi-agent Reinforcement Learning(MARL) method for coordinating multiple vehicles in the framework of an AVP system. This method utilizes traditional trajectory planning to accelerate the learning process and introduces collision conflict constraints for policy optimization to mitigate the path conflict problem. In contrast to other centralized multi-agent path finding methods, the proposed approach is scalable, distributed, and adapts to dynamic stochastic scenarios. We train the models in random scenarios and validate in several artificially designed complex parking scenarios where vehicles are always disturbed by dynamic and static obstacles. Experimental results show that our approach mitigates path conflicts and excels in terms of success rate and efficiency.

Underwater robots typically rely on acoustic sensors like sonar to perceive their surroundings. However, these sensors are often inundated with multiple sources and types of noise, which makes using raw data for any meaningful inference with features, objects, or boundary returns very difficult. While several conventional methods of dealing with noise exist, their success rates are unsatisfactory. This paper presents a novel application of conditional Generative Adversarial Networks (cGANs) to train a model to produce noise-free sonar images, outperforming several conventional filtering methods. Estimating free space is crucial for autonomous robots performing active exploration and mapping. Thus, we apply our approach to the task of underwater occupancy mapping and show superior free and occupied space inference when compared to conventional methods.

This paper proposes the concept design of a novel XY compliant parallel manipulator (CPM) with spatial configuration, which is beneficial to promote the performance of the XY CPM. Evolved from a planar configuration, a spatial compliant parallelogram flexure is devised as the basic module structure. Then, a mirror-symmetric XY CPM adopting spatial layout is proposed based on four-prismatic-prismatic (4-PP) parallel mechanism. The prototypes are fabricated by 3D printing for testing. The performance analysis and verification is conducted through theoretical modeling, finite element simulation, and experimental study. For comparison study, a planar XY CPM with similar mechanism is also developed. Results show that the proposed XY CPM with spatial configuration provides the benefits of smaller plane footprint, large working stroke, and enhanced load-bearing capacity as compared to the planar one. It is appropriate for precise positioning scenarios, like soft-contact lithography, which require high loading capacity and great compactness.

In very high-dimensional (≫10)(\gg 10) spaces, a collection of points generated uniformly at random will concentrate very tightly about its expected value - defying intuition developed in low-dimensional spaces. This paper explores the implications of this for two major classes of sample-based robot motion planning algorithms: Rapidly Exploring Random Trees (RRTs) and Probabilistic Road Maps (PRMs). First we show that the graph vertices concentrate in a thin-shelled hyper-sphere, with almost none near the origin nor at the edges of the workspace. Next we examine how varying one of the algorithms' parameters - the maximum edge length- can dramatically alter the algorithms' complexity and the connectivity of the resulting graph. Finally, we explore how the position of the initial node, often placed arbitrarily, can impact the shape of the graph. While the contributions of this paper are largely theoretical, many robotic applications of practical interest have extremely high-dimensional configuration spaces including humanoids, swarms and soft (a.k.a. continuum) robotics.