IROS 2023 论文列表

Sub-gram flying robots have transformative potential in applications from search and rescue to precision agriculture to environmental monitoring. However, a key gap in achieving autonomous flight for these applications is the low lift to weight ratio of flapping wing and quadrotor designs around 1 g or less. To close this gap, we propose a helictoper-style design that minimizes size and weight by leveraging the high lift, reliability, and low-voltage of sub-gram motors. We take an important step to enable this goal by designing a light-weight, micfrofabricated flybar mechanism to passively stabilize such a robot. Our 48 mg flybar is folded from a flat carbon fiber laminate into a 3D mechanism that couples tilting of the flybar to a change in the angle of attack of the rotors. Our design uses flexure joints instead of ball-in-socket joints common in larger flybars. To expedite the design exploration and optimization of a microfabricated flat-folded flybar, we develop a novel user-in-the-loop bi-level optimization workflow that combines Bayesian optimization design tools and expert feedback. We develop four template designs and use this method to achieve a peak damping ratio of 0.528, an 18.9x improvement from our initial design. Compared to a flybar-less rotor with a near 0 damping ratio, our flybar-rotor mechanism maintains a stable roll and pitch with relative deviations < 1°. Our results show that, if combined with a counter-torque mechanism such as a tail rotor, our miniaturized flybar could mechanically provide attitude stability for a sub-gram helicopter.

Humans are well-adept at navigating public spaces shared with others, where current autonomous mobile robots still struggle: while safely and efficiently reaching their goals, humans communicate their intentions and conform to unwritten social norms on a daily basis; conversely, robots become clumsy in those daily social scenarios, getting stuck in dense crowds, surprising nearby pedestrians, or even causing collisions. While recent research on robot learning has shown promises in data-driven social robot navigation, good-quality training data is still difficult to acquire through either trial and error or expert demonstrations. In this work, we propose to utilize the body of rich, widely available, social human navigation data in many natural human-inhabited public spaces for robots to learn similar, human-like, socially compliant navigation behaviors. To be specific, we design an open-source egocentric data collection sensor suite wearable by walking humans to provide multimodal robot perception data; we collect a large-scale (~100 km, 20 hours, 300 trials, 13 humans) dataset in a variety of public spaces which contain numerous natural social navigation interactions; we analyze our dataset, demonstrate its usability, and point out future research directions and use cases.11Website: https://cs.gmu.edu/-xiao/Research/MuSoHu/

Increased usage of additive manufacturing (AM) in various industries has solidified its role as an advanced manufacturing technique. However, there is an inherent lack of reliability in AM processes, particularly common in extrusion or deposition-based methods due to the stochastic nature of ma-terial deposition. This necessitates an intelligent manufacturing solution to address the drawbacks of AM. Thus, we propose a novel layer-wise approach toward closed-loop AM, which is capable of in-situ monitoring and repairing geometric defects. In this paper, we present a system that uses a robotic AM experimental platform that mimics a conventional open-loop fabrication setup, which we augment into a closed-loop system using two add-ons: in-situ inspection subsystem and online process correction subsystem. The in-situ inspection subsystem collects 3D point cloud scans and compares them against a reference CAD model, categorizing geometric deviations as positive or negative defects. Then the subsequent online process correction subsystem uses a re-plan and/or repair strategy to address the positive and/or negative defects, respectively. To evaluate this idea, we conducted three experiments on parts with manually induced defects to investigate the system's ability to repair those parts, thereby reducing defects, improving part accuracy, and enhancing mechanical properties. Comparing the defective and repaired parts, we observe a reduction in defect percent by volume from 10.7% to 1.3%, an improvement in geometric tolerance from 3.86% error to 0.08% error, and an increase in the part's breaking load from 4.77 kN to 6.31 kN. These experiments prove that our layer-wise closed-loop additive manufacturing approach improves the quality, tolerance, and reliability of plastic 3D printed parts, with the potential to extend to other extrusion/deposition-based AM processes, or even subtractive manufacturing and hybrid manufacturing methods.

Accurate shape reconstruction of transparent ob-jects is a challenging task due to their non-Lambertian surfaces and yet necessary for robots for accurate pose perception and safe manipulation. As vision-based sensing can produce erroneous measurements for transparent objects, the tactile modality is not sensitive to object transparency and can be used for reconstructing the object's shape. We propose AC-TOR, a novel framework for ACtive tactile-based category-level Transparent Object Reconstruction. ACTOR leverages large datasets of synthetic object with our proposed self-supervised learning approach for object shape reconstruction as the collection of real-world tactile data is prohibitively expensive. ACTOR can be used during inference with tactile data from category-level unknown transparent objects for reconstruction. Furthermore, we propose an active-tactile object exploration strategy as probing every part of the object surface can be sample inefficient. We also demonstrate tactile-based category-level object pose estimation task using ACTOR. We perform an extensive evaluation of our proposed methodology with real-world robotic experiments with comprehensive comparison studies with state-of-the-art approaches. Our proposed method outperforms these approaches in terms of tactile-based object reconstruction and object pose estimation.

The perception-aware motion planning method based on the localization uncertainty has the potential to improve the localization accuracy for robot navigation. How-ever, most of the existing perception-aware methods pre-build a global feature map and can not generate the perception- aware trajectory in real time. This paper proposes a topology- guided perception-aware receding horizon trajectory generation method, which contains a topology-guided position trajectory generation and a perception-aware yaw angle trajectory generation. Specifically, a memorable active map is built by selectively storing the visual landmarks. After that, a library of candidate topological trajectories are generated, which are then evaluated in terms of the perception quality based on the active map, smoothness, collision possibility and feasibility. In addition, the yaw angle trajectory is obtained through a front-end multiple refined path search and a back-end path- guided trajectory optimization. Comparative simulation and real-world experiments are carried out to confirm that the proposed method can keep more visual features in view and reduce the localization error.

Modular Reconfigurable Robots (MRRs) represent an exciting path forward for industrial robotics, opening up new possibilities for robot design. Compared to monolithic manipulators, they promise greater flexibility, improved maintainability, and cost-efficiency. However, there is no tool or standardized way to model and simulate assemblies of modules in the same way it has been done for robotic manipulators for decades. We introduce the Toolbox for Industrial Modular Robotics (Timor), a Python toolbox to bridge this gap and integrate modular robotics into existing simulation and optimization pipelines. Our open-source library offers model generation and task-based configuration optimization for MRRs. It can easily be integrated with existing simulation tools - not least by offering URDF export of arbitrary modular robot assemblies. Moreover, our experimental study demonstrates the effectiveness of Timor as a tool for designing modular robots optimized for specific use cases.

The kinematics of cuspidal 3R regional robots was studied extensively in the past. Moreover, certain industrial 6R robots were found to be cuspidal (e.g. Fanuc CRX series, Kinova GEN2), which makes cuspidal robots finally interesting for practical applications. This necessitates optimal trajectory planning, respecting the dynamics and technical limits of the particular robot. In this paper, a method for singularity-free time-optimal point-to-point trajectory (PtP) trajectory planning is proposed. As a special case, this method is applicable to time-optimal singularity-free assembly mode changing. Results are shown for 3R robots and a 6R Fanuc CRX10iA/L.

One way of ensuring operator's safety during human-robot collaboration is through Speed and Separation Monitoring (SSM), as defined in ISO standard ISO/TS 15066. In general, it is impossible to avoid all human-robot collisions: consider for instance the case when the robot does not move at all, a human operator can still collide with it by hitting it of her own voluntary motion. In the SSM framework, it is possible however to minimize harm by requiring this: if a collision ever occurs, then the robot must be in a stationary state (all links have zero velocity) at the time instant of the collision. In this paper, we propose a time-optimal control policy based on Time-Optimal Path Parameterization (TOPP) to guarantee such a behavior. Specifically, we show that: for any robot motion that is strictly faster than the motion recommended by our policy, there exists a human motion that results in a collision with the robot in a non-stationary state. Correlatively, we show, in simulation, that our policy is strictly less conservative than state-of-the-art safe robot control methods. Additionally, we propose a parallelization method to reduce the computation time of our pre-computation phase (down to about 0.5 sec, practically), which enables the whole pipeline (including the pre-computation) to be executed at runtime, nearly in real-time. Finally, we demonstrate the application of our method in a scenario: time-optimal, safe control of a 6-dof industrial robot.

Least-squares programming is a popular tool in robotics due to its simplicity and availability of open-source solvers. However, certain problems like sparse programming in the \ell_{0}\ell_{0}- or \ell_{0}-\mathbf{norm}\ell_{0}-\mathbf{norm} for time-optimal control are not equivalently solvable. In this work, we propose a non-linear hierarchical least-squares programming (NL-HLSP) for time-optimal control of non-linear discrete dynamic systems. We use a continuous approximation of the heaviside step function with an additional term that avoids vanishing gradients. We use a simple discretization method by keeping states and controls piece-wise constant between discretization steps. This way, we obtain a comparatively easily implementable NL-HLSP in contrast to direct transcription approaches of optimal control. We show that the NL-HLSP indeed recovers the discrete time-optimal control in the limit for resting goal points. We confirm the results in simulation for linear and non-linear control scenarios.

A biped robot walking in a crowd must avoid falls and collisions at the same time. The latter is usually addressed through Passive Safety (PS), which guarantees that the robot is at rest when a collision is inevitable. Since PS may limit the robot's mobility, the purpose of this work is to introduce and explore the novel concept of Time To Danger (TTD) as an alternative. For a given robot motion, TTD is the time where the robot enters the region that a person can potentially occupy in the future. After having studied the properties of TTD, a novel locomotion strategy is proposed, which computes an optimal locomotion plan that guarantees balance preservation and TTD maximization, following a receding horizon Model Predictive Control scheme. Controlled experiments in a challenging simulated crowd scenario demonstrate how the novel locomotion strategy outperforms a Passive Safety-based locomotion strategy from a collision avoidance point of view.

This paper proposes a tightly-coupled visual-Doppler-Velocity-Log (visual-DVL) fusion method for underwater robot localization through integrating the velocity measurements from a DVL into a visual odometry (VO). Considering that employing the DVL measurements in dead-reckoning systems easily leads to error accumulation and suboptimal results in previous works, we directly integrate them into the visual tracking process. Specifically, the velocity measurements are utilized to improve the initial estimation of camera pose during visual tracking, aiming to provide a better initial value for pose optimization. Thereafter, these velocity measurements are also directly employed to constrain the position change of the camera between two adjacent frames by constructing a novel DVL error term, which is optimized jointly with the visual constrains to obtain a more accurate camera pose. Various experiments are carried out in the datasets collected from several scenarios of the underwater simulation environment HoloOcean, and the results illustrate that the proposed fusion method can effectively improve the localization accuracy for underwater robots by about 20% compared to pure visual odometry. The proposed method provides valuable guidance for the accurate localization of underwater robots.

Underwater robots, like Autonomous Underwater Vehicles (AUVs) and Remotely Operated Vehicles (ROVs), are promising tools for the exploration and study of the under-ice environment and the ecosystems that thrive there. However, state estimation is a well-known problem for robotic systems, especially, for the ones that travel underwater. In this paper, wwe present a tightly-coupled multi-sensors fusion framework to increase localization accuracy that is robust to sensor failure. Visual images, Doppler Velocity Log (DVL), Inertial Measurement Unit (IMU) and Pressure sensor are integrated using a Multi-State Constraint Kalman Filter (MSCKF) for state estimation. Besides, a modified keyframe-based clone marginalization and a new DVL-aided feature enhancement method are presented to further improve the localization performance. The proposed method is validated in the under-ice environment on Lake Michigan, USA, and the results are cross-compared with 10 other different sensor fusion setups. Overall, the integration of keyframe enabled and DVL-aided feature enhancement yielded the best performance with a Root-mean-square error of less than 2 m compared to the ground truth path over a total traveling distance of about 200 m.

Operating unmanned aerial vehicles (UAVs) in complex environments that feature dynamic obstacles and external disturbances poses significant challenges, primarily due to the inherent uncertainty in such scenarios. Additionally, inaccurate robot localization and modeling errors further exacerbate these challenges. Recent research on UAV motion planning in static environments has been unable to cope with the rapidly changing surroundings, resulting in trajectories that may not be feasible. Moreover, previous approaches that have addressed dynamic obstacles or external disturbances in isolation are insufficient to handle the complexities of such environments. This paper proposes a reliable motion planning framework for UAVs, integrating various uncertainties into a chance constraint that characterizes the uncertainty in a probabilistic manner. The chance constraint provides a probabilistic safety certificate by calculating the collision probability between the robot's Gaussian-distributed forward reachable set and states of obstacles. To reduce the conservatism of the planned trajectory, we propose a tight upper bound of the collision probability and evaluate it both exactly and approximately. The approximated solution is used to generate motion primitives as a reference trajectory, while the exact solution is leveraged to iteratively optimize the trajectory for better results. Our method is thoroughly tested in simulation and real-world experiments, verifying its reliability and effectiveness in uncertain environments.

For a robot to personalize physical assistance effectively, it must learn user preferences that can be generally reapplied to future scenarios. In this work, we investigate personalization of household cleanup with robots that can tidy up rooms by picking up objects and putting them away. A key challenge is determining the proper place to put each object, as people's preferences can vary greatly depending on personal taste or cultural background. For instance, one person may prefer storing shirts in the drawer, while another may prefer them on the shelf. We aim to build systems that can learn such preferences from just a handful of examples via prior interactions with a particular person. We show that robots can combine language-based planning and perception with the few-shot summarization capabilities of large language models (LLMs) to infer generalized user preferences that are broadly applicable to future interactions. This approach enables fast adaptation and achieves 91.2% accuracy on unseen objects in our benchmark dataset. We also demonstrate our approach on a real-world mobile manipulator called TidyBot, which successfully puts away 85.0% of objects in real-world test scenarios.

Autonomous ultrasound (US) imaging has gained increased interest recently, and it has been seen as a potential solution to overcome the limitations of free-hand US exami-nations, such as inter-operator variations. However, it is still challenging to accurately map planned paths from a generic atlas to individual patients, particularly for thoracic applications with high acoustic-impedance bone structures below the skin. To address this challenge, a dense graph-based non-rigid registration is proposed to transfer planned paths from the atlas to the current setup by explicitly considering subcutaneous bone surface. To this end, the sternum and cartilage branches are segmented using a template matching to assist coarse alignment of US and CT point clouds. Afterward, a directed graph is generated based on the CT template. Then, the self-organizing map using geographical distance is successively performed twice to extract the optimal graph representations for CT and US point clouds, individually. To evaluate the proposed approach, five cartilage point clouds from distinct patients are employed. The results demonstrate that the proposed graph-based registration can effectively map trajectories from CT to the current setup to do US examination through limited intercostal space. The non-rigid registration results in terms of Hausdorff distance (Mean±SD) is 9.48 \pm 0.279.48 \pm 0.27 mm and the path transferring error in terms of Euclidean distance is 2.21\pm 1.11\ mm2.21\pm 1.11\ mm. The code11https://github.com/marslicy/Cartilage-graph-based-US-CT-Registration and video22Video: https://www.youtube.com/watch?v=QJz2fkwgbP8 can be publicly accessed.

Robotic manipulators deal with serious issues due to their absolute positioning error. This error is usually compensated by an operator in classical robot programming using the teach-and-play method. However, it has a significant effect on accuracy of robotic guidance systems (RGS) that automatically generate process tool trajectory based on the measured data from a sensor. In this paper, we firstly describe the various components of an RGS that affect its overall accuracy. We then introduce a proposed model for the calibration process (MCP) that can be used to analyze the effect of absolute positioning errors on the accuracy of hand-eye calibration, six-point calibration of a process tool and mutual transformation between these tools. Simulations were used to evaluate the proposed MCP model. The results of this analysis are crucial for the practical use of RGS.

The human limb possesses a remarkable capacity to absorb energy during physical human-robot interaction (pHRI), which can be quantified as the biomechanical “Excess of Passivity” (EoP) using non-linear control theory. This biome-chanical passivity index can be used to reduce conservatism and increase the transparency of pHRI stabilizers. Previous work on EoP has used system identification techniques to compute EoP offline. However, for use in real-time controllers, an instantaneous method for EoP estimation would be desired. This paper hypothesizes that muscle fatigue can potentially be a complicating factor which can cumulatively affect the ability of human biomechanics to absorb mechanical energy over time during physical interaction with robots. In this work, we focused on the energetic behavior of the human wrist during pHRI, and, for the first time, we investigated the effect of fatigue on EoP. The EoP for five participants was computed throughout one hundred-second trials of high-frequency wrist perturbations in four directions. Subjects maintained a stiff and consistent grip throughout each trial, causing an accumulation of fatigue in the forearm muscles. Muscle activity was recorded using an array of sixteen sEMG sensors. It was found that the EoP degraded (in a statistically significant manner) with increased muscle fatigue in all directions, even when the level of muscle co-contraction was controlled consistently through a visual myofeedback mechanism. 100% of the subjects exhibited this decline in energy absorption capacity in all directions studied. The median drop in EoP after one-hundred seconds of perturbation was 11% for trials in the abduction and adduction directions and 22% in the pronation and supination directions. These results indicate a need for more robust estimation methods or new modalities to account for muscle fatigue in the control architectures of physical human-robot interaction.

In this study, we propose a novel approach for investigating optimization performance by flexible robot co-ordination in automated warehouses with multi-agent rein-forcement learning (MARL)-based control. Automated systems using robots are expected to achieve efficient operations compared with manual systems in terms of overall optimization performance. However, the impact of overall optimization on performance remains unclear in most automated systems due to a lack of suitable control methods. Thus, we proposed a centralized training-and-decentralized execution MARL frame-work as a practical overall optimization control method. In the proposed framework, we also proposed a single shared critic, trained with global states and rewards, applicable to a case in which heterogeneous agents make decisions asynchronously. Our proposed MARL framework was applied to the task selection of material handling equipment through automated order picking simulation, and its performance was evaluated to determine how far overall optimization outperforms partial optimization by comparing it with other MARL frameworks and rule-based control methods.