ICRA 2023 论文列表

Concentric tube continuum robots (CTCRs) belong to the family of continuum robots with applications in minimally invasive surgeries. Because of this application domain, measuring the external forces along the body of the robot is paramount. CTCRs are made up of thin elastic rods and are intended to be applied inside the human body, where conventional sensor-based measurements are not feasible. Consequently, research is resorting to estimate the forces through geometric, numeric, or optimization methods. However, these methods often suffer from slow convergence. In this paper, we introduce a novel data-driven approach for estimating contact forces along the body of a CTCR that offers an estimation precision comparable to the current state-of-the-art optimization-based approaches, but exhibits nearly two orders of magnitude faster convergence. The proposed method is scalable and exhibits a significant performance in response to a wide range of external forces. The approach was evaluated in simulations and on a real 2-tube CTCR.

We study landmark-based SLAM with unknown data association: our robot navigates in a completely unknown environment and has to simultaneously reason over its own trajectory, the positions of an unknown number of landmarks in the environment, and potential data associations between measurements and landmarks. This setup is interesting since: (i) it arises when recovering from data association failures or from SLAM with information-poor sensors, (ii) it sheds light on fundamental limits (and hardness) of landmark-based SLAM problems irrespective of the front-end data association method, and (iii) it generalizes existing approaches where data association is assumed to be known or partially known. We approach the problem by splitting it into an inner problem of estimating the trajectory, landmark positions and data associations and an outer problem of estimating the number of landmarks. Our approach creates useful and novel connections with existing techniques from discrete-continuous optimization (e.g., k-means clustering), which has the potential to trigger novel research. We demonstrate the proposed approaches in extensive simulations and on real datasets and show that the proposed techniques outperform typical data association baselines and are even competitive against an “oracle” baseline which has access to the number of landmarks and an initial guess for each landmark.

Vision-based tactile sensors that can measure 3D geometry of the contacting objects are crucial for robots to perform dexterous manipulation tasks. However, the existing sensors are usually complicated to fabricate and delicate to extend. In this work, we novelly take advantage of the reflection property of semitransparent elastomer to design a robust, low-cost, and easy-to-fabricate tactile sensor named DTact. DTact measures high-resolution 3D geometry accurately from the darkness shown in the captured tactile images with only a single image for calibration. In contrast to previous sensors, DTact is robust under various illumination conditions. Then, we build prototypes of DTact that have non-planar contact surfaces with minimal extra efforts and costs. Finally, we perform two intelligent robotic tasks including pose estimation and object recognition using DTact, in which DTact shows large potential in applications.

Occupancy mapping has been widely utilized to represent the surroundings for autonomous robots to perform tasks such as navigation and manipulation. While occupancy mapping in 2-D environments has been well-studied, there have been few approaches suitable for 3-D dynamic occupancy mapping which is essential for aerial robots. This paper presents a novel 3-D dynamic occupancy mapping algorithm called DS-K3DOM. We first establish a Bayesian method to sequentially update occupancy maps for a stream of measurements based on the random finite set theory. Then, we approximate it with particles in the Dempster-Shafer domain to enable real-time computation. Moreover, the algorithm applies kernel-based inference with Dirichlet basic belief assignment to enable dense mapping from sparse measurements. The efficacy of the proposed algorithm is demonstrated through simulations and real experimentsiiThe code is available at: https://github.com/JuyeopHan/dsk3dom_public.

Untethered magnetic microrobots with control-lable locomotion property and multiple functions have attracted lots of attention in recent years. Owing to the small scale, micro-robots with automatic navigation possess a promising perspec-tive for biomedical applications including precise delivery and targeted therapy in confined and narrow space, especially for in-vivo scenario. However, the practical working environment for microrobots can be various, dynamic, and complicated, and path planning algorithm applicable for both dynamic obstacle avoidance and planning in maze-like environments still remains a challenge. Furthermore, considering the sizes, different types of microrobots may occupy different proportions of the field of vision. The safe distance between the waypoints and the obstacles needs to be taken into thoughts. In this work, we proposed a reinforcement learning-based strategy capable of real-time path planning for microrobots in different scales. The reference moving direction at each control period is provided by a deep Q network (DQN) according to the local surrounding environment, and the corresponding control magnetic field is generated via a 3-axis Helmholtz coil system. A distur-bance observer (DOB) is responsible for the locomotion state observation and direction error compensation. Experiments demonstrate the effectiveness of our proposed strategy using microrobots with different locomotion mechanisms and scales, in both virtual dynamic obstacle environments and channel-like environments.

Vision-based autonomous navigation systems rely on fast and accurate object detection algorithms to avoid obstacles. Algorithms and sensors designed for such systems need to be computationally efficient, due to the limited energy of the hardware used for deployment. Biologically inspired event cameras are a good candidate as a vision sensor for such systems due to their speed, energy efficiency, and robustness to varying lighting conditions. However, traditional computer vision algorithms fail to work on event-based outputs, as they lack photometric features such as light intensity and texture. In this work, we propose a novel technique that utilizes the temporal information inherently present in the events to efficiently detect moving objects. Our technique consists of a lightweight spiking neural architecture that is able to separate events based on the speed of the corresponding objects. These separated events are then further grouped spatially to determine object boundaries. This method of object detection is both asynchronous and robust to camera noise. In addition, it shows good performance in scenarios with events generated by static objects in the background, where existing event-based algorithms fail. We show that by utilizing our architecture, autonomous navigation systems can have minimal latency and energy overheads for performing object detection.

Human body motion prediction is a fundamental part of many human-robot applications. Despite the recent progress in the area, most studies predict human body motion relative to a fixed joint and only limit their model to predict one possible future motion, or both. However, due to the complex nature of human motion, a single prediction cannot adequately reflect the many possible movements one can make. Also, for any robotics application, prediction of the full human body motion including the absolute 3D trajectory - not just a 3D body pose relative to the hip joint - is needed. In this paper, we try to address these two shortcomings by proposing a transformer-based generative model for forecasting multiple diverse human motions. Our model generates NN future possible body motions given the human motion history. This is achieved by first predicting the pose of the body relative to the hip joint as was done in prior work. Then, our proposed Hip Prediction Module predicts the trajectory of the hip position relative to a global reference frame for each predicted pose frame, an aspect of human body motion neglected by previous work. To obtain a set of diverse predicted motions, we introduce a similarity loss that penalizes the pairwise sample distance. Our system not only outperforms the state-of-the-art in human motion prediction, but also is able to predict a diverse set of future human body motions, including the hip trajectory.

While manipulating rigid objects is an extensively explored research topic, deformable linear object (DLO) manipulation seems significantly underdeveloped. A potential reason for this is the inherent difficulty in describing and observing the state of the DLO as its geometry changes during manipulation. This paper proposes an algorithm for fast-tracking the shape of a DLO based on the masked image. Having no prior knowledge about the tracked object, the proposed method finds a reliable representation of the shape of the tracked object within tens of milliseconds. This algorithm's main idea is to first skeletonize the DLO mask image, walk through the parts of the DLO skeleton, arrange the segments into an ordered path, and finally fit a B-spline into it. Experiments show that our solution outperforms the State-of-the-Art approaches in DLO's shape reconstruction accuracy and algorithm running time and can handle challenging scenarios such as severe occlusions, self-intersections, and multiple DLOs in a single image.

Persistent multi-object tracking (MOT) allows autonomous vehicles to navigate safely in highly dynamic environments. One of the well-known challenges in MOT is object occlusion when an object becomes unobservant for subsequent frames. The current MOT methods store objects information, such as trajectories, in internal memory to recover the objects after occlusions. However, they retain short-term memory to save computational time and avoid slowing down the MOT method. As a result, they lose track of objects in some occlusion scenarios, particularly long ones. In this paper, we propose DFR-FastMOT, a light MOT method that uses data from a camera and LiDAR sensors and relies on an algebraic formulation for object association and fusion. The formulation boosts the computational time and permits long-term memory that tackles more occlusion scenarios. Our method shows outstanding tracking performance over recent learning and non-learning benchmarks with about 3% and 4% margin in MOTA, respectively. Also, we conduct extensive experiments that simulate occlusion phenomena by employing detectors with various distortion levels. The proposed solution enables superior performance under various distortion levels in detection over current state-of-art methods. Our framework processes about 7,763 frames in 1.48 seconds, which is seven times faster than recent benchmarks. The framework will be available at https://github.com/MohamedNagyMostafa/DFR-FastMOT.

This paper addresses the problem of calibrating extrinsic parameter matrix between an RGB camera and a LiDAR. Multimodal sensing systems are essential for fully autonomous navigation platforms. A key pre-requisite for such a system is calibration between different sensors. As the two most widely equipped sensors, calibration between RGB cameras and LiDARs remains challenging. Existing methods address this problem without using explicit geometric priors. In this paper, we propose a novel real-time network that utilizes depth-discontinuous edges extracted from a single image to calibrate cameras and LiDARs. Our network consists of two key components: (1) a self-supervised edge extraction network named DEdgeNet, which detects depth-discontinuous edges from a single image and extracts corresponding features; (2) prediction of the extrinsic parameter matrix between the camera and the LiDAR by matching fixed features in RGB images and updating depth features in a coarse-to-fine frame. Specifically, considering that edges are rich and common in natural scenes, DEdgeNet simplifies RGB image encoding and extracts fixed edges for feature matching. We conducted extensive experiments on the KITTI-odometry dataset. The results show that our method achieves an average rotation error of 0.028° and an average translation error of 0.247 cm, which demonstrates the superiority of our method.

In this paper, we present a simple yet effective semi-supervised 3D object detector named DDS3D. Our main contributions have two-fold. On the one hand, different from previous works using Non-Maximal Suppression (NMS) or its variants for obtaining the sparse pseudo labels, we propose a dense pseudo-label generation strategy to get dense pseudo-labels, which can retain more potential supervision information for the student network. On the other hand, instead of traditional fixed thresholds, we propose a dynamic threshold manner to generate pseudo-labels, which can guarantee the quality and quantity of pseudo-labels during the whole training process. Benefiting from these two components, our DDS3D outperforms the state-of-the-art semi-supervised 3d object detection with mAP of 3.1% on the pedestrian and 2.1% on the cyclist under the same configuration of 1% samples. Extensive ablation studies on the KITTI dataset demonstrate the effectiveness of our DDS3D. The code and models will be made publicly available at https://github.com/hust-jy/DDS3D

Autonomous driving has attracted lots of attention in recent years. For some tasks, e.g., trajectory prediction, motion planning, and trajectory tracking, an accurate vehicle model can reduce the difficulty of these tasks and improve task completion performance. Prior works focused on parameter estimation of physical models or modeling nonlinear dynamics using neural networks. Still, these methods rely on internal parameters of vehicles or are not friendly for control due to the strong nonlinearity of models. This paper proposes a data-driven method to approximate vehicle dynamics based on the Koopman operator. The resulting model is an interpretable linear time-invariant model, facilitating controller design and solving related optimization problems. In the proposed approach, the state transition matrix is constructed based on the learned Koopman eigenvalues, while the input matrix is trained as a tensor. Based on the resulting model, a linear model predictive controller is designed to implement coupled longitudinal and lateral trajectory tracking. Simulations and experiments, including vehicle dynamics modeling and coupled longitudinal and lateral trajectory tracking, are performed in a high-fidelity CarSim environment and a real vehicle platform. An oil-driven D-Class SUV is selected in the simulation, while a real electric SUV is utilized in the experiment. Simulation and experiment results illustrate that the model of the nonlinear vehicle dynamics can be identified effectively via the proposed method, and high-quality trajectory tracking performance can be obtained with the resulting model.

In this paper, we propose a multi-object tracking framework for videos captured by UAVs, considering motion imperfection in the following two aspects: 1) motion blurring of objects due to high-speed motion of the UAV and the objects, deteriorating the performance of the detector; 2) motion coupling of the global movement of the UAV camera with the object motion, resulting in the nonlinearity of objects trajectories in adjacent frames and further more difficult to predict. For motion blurring, this paper proposes a hybrid deblurring module that deals with the blurred frames while retaining the clear frames, trading off between video tracking performance and spatio-temporal consistency. For motion coupling, we proposed a motion compensation module to align adjacent frames by feature matching, and the corrected target position is obtained in the next frame to alleviate the interference of camera movement with tracking. We evaluate the proposed methods on VisDrone dataset and validate that our framework achieves new state-of-the-art performance on UAV-based MOT systems.

With robots being deployed in increasingly complex environments like underground mines and planetary surfaces, the multi-sensor fusion method has gained more and more attention which is a promising solution to state estimation in the such scene. The fusion scheme is a central component of these methods. In this paper, a light-weight iEKF-based LiDAR-inertial odometry system is presented, which utilizes a degeneration-aware and modular sensor-fusion pipeline that takes both LiDAR points and relative pose from another odometry as the measurement in the update process only when degeneration is detected. Both the Cramer-Rao Lower Bound (CRLB) theory and simulation test are used to demonstrate the higher accuracy of our method compared to methods using a single observation. Furthermore, the proposed system is evaluated in perceptually challenging datasets against various state-of-the-art sensor-fusion methods. The results show that the proposed system achieves real-time and high estimation accuracy performance despite the challenging environment and poor observations.

Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information. However, the state-of-the-art (SoTA) surface normal estimators (SNEs) generally suffer from an unsatisfactory trade-off between efficiency and accuracy. To resolve this dilemma, this paper first presents a superfast depth-to-normal translator (D2NT), which can directly translate depth images into surface normal maps without calculating 3D coordinates. We then propose a discontinuity-aware gradient (DAG) filter, which adaptively generates gradient convolution kernels to improve depth gradient estimation. Finally, we propose a surface normal refinement module that can easily be integrated into any depth-to-normal SNEs, substantially improving the surface normal estimation accuracy. Our proposed algorithm demonstrates the best accuracy among all other existing real-time SNEs and achieves the SoTA trade-off between efficiency and accuracy.

Centralized approaches for multi-robot coverage planning problems suffer from the lack of scalability. Learning-based distributed algorithms provide a scalable avenue in addition to bringing data-oriented feature generation capabilities to the table, allowing integration with other learning-based approaches. To this end, we present a learning-based, differentiable distributed coverage planner (D2CoPLAN) which scales efficiently in runtime and number of agents compared to the expert algorithm, and performs on par with the classical distributed algorithm. In addition, we show that D2CoPLANcan be seamlessly combined with other learning methods to learn end-to-end, resulting in a better solution than the individually trained modules, opening doors to further research for tasks that remain elusive with classical methods.

LiDAR sensors are widely used for 3D object detection in various mobile robotics applications. LiDAR sensors continuously generate point cloud data in real-time. Conventional 3D object detectors detect objects using a set of points acquired over a fixed duration. However, recent studies have shown that the performance of object detection can be further enhanced by utilizing spatio-temporal information obtained from point cloud sequences. In this paper, we propose a new 3D object detector, named D-Align, which can effectively produce strong bird's-eye-view (BEV) features by aligning and aggregating the features obtained from a sequence of point sets. The proposed method includes a novel dual-query co-attention network that uses two types of queries, including target query set (T-QS) and support query set (S-QS), to update the features of target and support frames, respectively. D-Align aligns S-QS to T-QS based on the temporal context features extracted from the adjacent feature maps and then aggregates S-QS with T-QS using a gated fusion mechanism. The dual queries are updated through multiple attention layers to progressively enhance the target frame features used to produce the detection results. Our experiments on the nuScenes dataset show that the proposed D-Align method greatly improved the performance of a single frame-based baseline method and significantly outperformed the latest 3D object detectors. Code is available at https://github.com/junhyung-SPALab/D-Align.

3D lane detection is an integral part of au-tonomous driving systems. Previous CNN and Transformer-based methods usually first generate a bird's-eye-view (BEV) feature map from the front view image, and then use a sub-network with BEV feature map as input to predict 3D lanes. Such approaches require an explicit view transformation between BEV and front view, which itself is still a challenging problem. In this paper, we propose CurveFormer, a single-stage Transformer-based method that directly calculates 3D lane pa-rameters and can circumvent the difficult view transformation step. Specifically, we formulate 3D lane detection as a curve propagation problem by using curve queries. A 3D lane query is represented by a dynamic and ordered anchor point set. In this way, queries with curve representation in Transformer decoder iteratively refine the 3D lane detection results. Moreover, a curve cross-attention module is introduced to compute the similarities between curve queries and image features. Additionally, a context sampling module that can capture more relative image features of a curve query is provided to further boost the 3D lane detection performance. We evaluate our method for 3D lane detection on both synthetic and real-world datasets, and the experimental results show that our method achieves promising performance compared with the state-of-the-art approaches. The effectiveness of each component is validated via ablation studies as well.

We present a novel Curvature-Aware Model Pre-dictive Contouring Control (CA-MPCC) formulation for mobile robotics motion planning. Our method aims at generalizing the traditional contouring control formulation derived from machining to autonomous driving applications. The proposed controller is able of handling sharp curvatures in the reference path while subject to non-linear constraints, such as lane boundaries and dynamic obstacle collision avoidance. Com-pared to a standard MPCC formulation, our method improves the reliability of the path-following algorithm and simplifies the tuning, while preserving real-time capabilities. We validate our findings in both simulations and experiments on a scaled-down car-like robot.