IROS 2024 论文列表

This paper addresses the challenge of acoustic scene mapping (ASM) in complex indoor environments with multiple sound sources. Unlike existing methods that rely on prior data association or SLAM frameworks, we propose a novel particle filter-based iterative framework, termed I-ASM, for ASM using a mobile robot equipped with a microphone array and LiDAR. I-ASM harnesses an innovative "implicit association" to align sound sources with Direction of Arrival (DoA) observations without requiring explicit pairing, thereby streamlining the mapping process. Given inputs including an occupancy map, DoA estimates from various robot positions, and corresponding robot pose data, I-ASM performs multi-source mapping through an iterative cycle of "Filtering-Clustering-Implicit Associating". The proposed framework has been tested in real-world scenarios with up to 10 concurrent sound sources, demonstrating its robustness against missing and false DoA estimates while achieving high-quality ASM results. To benefit the community, we open-source all the codes and data at https://github.com/AISLAB-sustech/Acoustic-Scene-Mapping

3D contrastive representation learning has exhibited remarkable efficacy across various downstream tasks. However, existing contrastive learning paradigms based on cosine similarity fail to deeply explore the potential intra-modal hierarchical and cross-modal semantic correlations about multi-modal data in Euclidean space. In response, we seek solutions in hyperbolic space and propose a hyperbolic image-and-pointcloud contrastive learning method (HyperIPC). For the intra-modal branch, we rely on the intrinsic geometric structure to explore the hyperbolic embedding representation of point cloud to capture invariant features. For the cross-modal branch, we leverage images to guide the point cloud in establishing strong semantic hierarchical correlations. Empirical experiments underscore the outstanding classification performance of HyperIPC. Notably, HyperIPC enhances object classification results by 2.8% and few-shot classification outcomes by 5.9% on ScanObjectNN compared to the baseline. Furthermore, ablation studies and confirmatory testing validate the rationality of HyperIPC’s parameter settings and the effectiveness of its submodules.

To achieve dexterity comparable to that of humans, robots must intelligently process tactile sensor data. Taxel-based tactile signals often have low spatial-resolution, with non-standardized representations. In this paper, we propose a novel framework, HyperTaxel, for learning a geometrically-informed representation of taxel-based tactile signals to address challenges associated with their spatial resolution. We use this representation and a contrastive learning objective to encode and map sparse low-resolution taxel signals to high-resolution contact surfaces. To address the uncertainty inherent in these signals, we leverage joint probability distributions across multiple simultaneous contacts to improve taxel hyper-resolution. We evaluate our representation by comparing it with two baselines and present results that suggest our representation outperforms the baselines. Furthermore, we present qualitative results that demonstrate the learned representation captures the geometric features of the contact surface, such as flatness, curvature, and edges, and generalizes across different objects and sensor configurations. Moreover, we present results that suggest our representation improves the performance of various downstream tasks, such as surface classification, 6D in-hand pose estimation, and sim-to-real transfer.

Soft growing vine robots show great potential for navigation and decontamination tasks in the nuclear industry. This paper introduces a novel hybrid continuum-eversion robot designed to address certain challenges in relation to navigating and operating within pipe networks and enclosed remote vessels. The hybrid robot combines the flexibility of a soft eversion robot with the precision of a continuum robot at its tip, allowing for controlled steering and movement in hard to access and/or complex environments. The design enables the delivery of sensors, liquids, and aerosols to remote areas, supporting remote decontamination activities.This paper outlines the design and construction of the robot and the methods by which it achieves selective steering. We also include a comprehensive review of current related work in eversion robotics, as well as other steering devices and actuators currently under research, which underpin this novel active steering approach. This is followed by an experimental evaluation that demonstrates the robot’s real-world capabilities in delivering liquids and aerosols to remote locations. The experiments reveal successful outcomes, with over 95% success in precision spraying tests. The paper concludes by discussing future work alongside limitations in the current design, ultimately showcasing its potential as a solution for remote decontamination operations in the nuclear industry.

Soft exoskeleton robots have promising potential in walking assistance with comfortable wearing experience. In this study, an exosuit equipped with a twisted string actuator (TSA) is developed to provide powerful driving force and diverse operating modes for hemiplegic patients in daily life. It is challenging to establish the human-robot coupling dynamic model due to the soft structure of the exosuit and tight coupling, precise control and effective assistance are difficult to guaranteed in current exosuits. Considering the impedance characteristics of human-robot interaction, an adaptive impedance control method based on reinforcement learning (RL) is proposed, where human motion intention is utilized to optimize impedance parameters and adjust the robot's operating mode. A nonlinear disturbance observer is proposed to compensate for the effects of model estimation errors, joint friction, and external disturbances. Experimental verification demonstrates the effectiveness and superiority of the robotic system.

Reliable Human Orientation Estimation (HOE) from a monocular image is critical for autonomous agents to understand human intention. Significant progress has been made in HOE under full observation. However, the existing methods easily make a wrong prediction under partial observation and give it an unexpectedly high confidence. To solve the above problems, this study first develops a method called Part-HOE that estimates orientation from the visible joints of a target person so that it is able to handle partial observation. Subsequently, we introduce a confidence-aware orientation estimation method, enabling more accurate orientation estimation and reasonable confidence estimation under partial observation. The effectiveness of our method is validated on both public and custom-built datasets, and it shows great accuracy and reliability improvement in partial observation scenarios. In particular, we show in real experiments that our method can benefit the robustness and consistency of the Robot Person Following (RPF) task.

As model and dataset sizes continue to scale in robot learning, the need to understand how the composition and properties of a dataset affect model performance becomes increasingly urgent to ensure cost-effective data collection and model performance. In this work, we empirically investigate how physics attributes (color, friction coefficient, shape) and scene background characteristics, such as the complexity and dynamics of interactions with background objects, influence the performance of Video Transformers in predicting planar pushing trajectories. We investigate three primary questions: How do physics attributes and background scene characteristics influence model performance? What kind of changes in attributes are most detrimental to model generalization? What proportion of fine-tuning data is required to adapt models to novel scenarios? To facilitate this research, we present CloudGripper-Push-1K, a large real-world vision-based robot pushing dataset comprising 1278 hours and 460,000 videos of planar pushing interactions with objects with different physics and background attributes. We also propose Video Occlusion Transformer (VOT), a generic modular video-transformer-based trajectory prediction framework which features 3 choices of 2D-spatial encoders as the subject of our case study. The dataset and source code are available at https://cloudgripper.org.

Horticultural tasks such as pruning and selective harvesting are labor intensive and horticultural staff are hard to find. Automating these tasks is challenging due to the semi-structured greenhouse workspaces, changing environmental conditions such as lighting, dense plant growth with many occlusions, and the need for gentle manipulation of non-rigid plant organs. In this work, we present the three-armed system HortiBot, with two arms for manipulation and a third arm as an articulated head for active perception using stereo cameras. Its perception system detects not only peppers, but also peduncles and stems in real time, and performs online data association to build a world model of pepper plants. Collision-aware online trajectory generation allows all three arms to safely track their respective targets for observation, grasping, and cutting. We integrated perception and manipulation to perform selective harvesting of peppers and evaluated the system in lab experiments. Using active perception coupled with end-effector force torque sensing for compliant manipulation, HortiBot achieves high success rates in our indoor pepper plant mock-up.

Collaborative path planning for robot swarms in complex, unknown environments without external positioning is a challenging problem. This requires robots to find safe directions based on real-time environmental observations, and to efficiently transfer and fuse these observations within the swarm. This study presents a filtering method based on Fast Fourier Transform (FFT) to address these two issues. We treat sensors’ environmental observations as a digital sampling process. Then, we design two different types of filters for safe direction extraction, as well as for the compression and reconstruction of environmental data. The reconstructed data is mapped to probabilistic domain, achieving efficient fusion of swarm observations and planning decision. The computation time is only on the order of microseconds, and the transmission data in communication systems is in bit-level. The performance of our algorithm in sensor data processing was validated in real world experiments, and the effectiveness in swarm path optimization was demonstrated through extensive simulations.

The need for compliant and proprioceptive actuators has grown more evident in pursuing more adaptable and versatile robotic systems. Hydraulically Amplified Self-Healing Electrostatic (HASEL) actuators offer distinctive advantages with their inherent softness and flexibility, making them promising candidates for various robotic tasks, including delicate interactions with humans and animals, biomimetic locomotion, prosthetics, and exoskeletons. This has resulted in a growing interest in the capacitive self-sensing capabilities of HASEL actuators to create miniature displacement estimation circuitry that does not require external sensors. However, achieving HASEL self-sensing for actuation frequencies above 1 Hz and with miniature high-voltage power supplies has remained limited. In this paper, we introduce the F-HASEL actuator, which adds an additional electrode pair used exclusively for capacitive sensing to a Peano-HASEL actuator. We demonstrate displacement estimation of the F-HASEL during high-frequency actuation up to 20 Hz and during external loading using miniaturized circuitry comprised of low-cost off-the-shelf components and a miniature high-voltage power supply. Finally, we propose circuitry to estimate the displacement of multiple F-HASELs and demonstrate it in a wearable application to track joint rotations of a virtual reality user in real-time.

We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. To this end, we first propose a Gaussian densification strategy based on the rendering loss to map unobserved areas and refine reobserved areas. Second, we introduce extra regularization parameters to alleviate the "forgetting" problem during contiunous mapping, where parameters tend to overfit the latest frame and result in decreasing rendering quality for previous frames. Both mapping and tracking are performed with Gaussian parameters by minimizing re-rendering loss in a differentiable way. Compared to recent neural and concurrently developed Gaussian splatting RGBD SLAM baselines, our method achieves state-of-the-art results on the synthetic dataset Replica and competitive results on the real-world dataset TUM. The code is released on https://github.com/ljjTYJR/HF-SLAM.

Ultra-wide band (UWB) systems are gaining popularity for multi-robot localization benefiting from their high-accuracy ranging capabilities. However, current UWB systems fall short in determining orientations and realizing pair-wise localization for neglecting bearing information. Given the importance of bearing capabilities, especially when vision-based methods fail, this paper proposes a high-accuracy 2-D bearing estimation method using stereo UWB arrays. We propose a novel phase error calibration method that effectively mitigates various phase imperfections. This array is designed with antenna spacing larger than half the wavelength to diminish antenna coupling and enhance bearing accuracy. As regards the phase ambiguity issue arising from large antenna spacing, a distributed range-assisted phase ambiguity determination method is developed. Our bearing estimation method exhibits low complexity and is well-suited for the deployment on mobile robots with limited computational resources. The performance of the proposed method is validated on the practical platforms under dynamic scenarios, yielding root mean squared errors (RMSEs) less than 4° and 3° for azimuth and elevation angle estimation, respectively.

Needle-based procedures such as biopsies or radiofrequency ablation (RFA) of tumors are often considered to diagnose and treat liver cancer for their low invasiveness but raise difficulties for practitioners related to needle placement and visibility of internal anatomical structures. Efforts are being conducted to build real-time needle insertion simulators with both visual and haptic rendering, facing challenges related to model accuracy and real-time computational performance. This work focuses on the contact model involved in needle-tissue interactions in order to improve the realism of the resulting haptic rendering. We present a novel method to update the compliant coupling at high rates of a complete contact system involving the mechanics of a large object and the complete model of a flexible needle. These updates allow to adapt the contact directions to the needle deformations in the haptic thread, with the aim of improving the resulting haptic feedback. Updates of contact directions and the related mechanical system according to high-rate deformations decrease force feedback artifacts associated with low-rate mechanics while maintaining high-rate performances for the haptic loop.

Cooperative path planning, a crucial aspect of multi-agent systems research, serves a variety of sectors, including military, agriculture, and industry. Many existing algorithms, however, come with certain limitations, such as simplified kinematic models and inadequate support for multiple group scenarios. Focusing on the planning problem associated with a nonholonomic Ackermann model for Unmanned Ground Vehicles (UGV), we propose a leaderless, hierarchical Search-Based Cooperative Motion Planning (SCMP) method. The high-level utilizes a binary conflict search tree to minimize runtime, while the low-level fabricates kinematically feasible, collision-free paths that are shape-constrained. Our algorithm can adapt to scenarios featuring multiple groups with different shapes, outlier agents, and elaborate obstacles. We conduct algorithm comparisons, performance testing, simulation, and real-world testing, verifying the effectiveness and applicability of our algorithm. The implementation of our method will be open-sourced at https://github.com/WYCUniverStar/SCMP.

We consider a large-scale multi-robot path planning problem in a cluttered environment. Our approach achieves real-time replanning by dividing the workspace into cells and utilizing a hierarchical planner. Specifically, we propose novel multi-commodity flow-based high-level planners that route robots through cells with reduced congestion, along with an anytime low-level planner that computes collision-free paths for robots within each cell in parallel. A highlight of our method is a significant improvement in computation time. Specifically, we show empirical results of a 500-times speedup in computation time compared to the baseline multi-agent pathfinding approach on the environments we study. We account for the robot’s embodiment and support non-stop execution with continuous replanning. We demonstrate the real-time performance of our algorithm with up to 142 robots in simulation, and a representative 32 physical Crazyflie nanoquadrotor experiment.

In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach enables agents to form a global consensus from local observations, using it as an additional piece of information to guide collaborative actions during execution. To cater to the dynamic requirements of various tasks, consensus is divided into multiple layers, encompassing both short-term and long-term considerations. Short-term observations prompt the creation of an immediate, low-layer consensus, while long-term observations contribute to the formation of a strategic, high-layer consensus. This process is further refined through an adaptive attention mechanism that dynamically adjusts the influence of each consensus layer. This mechanism optimizes the balance between immediate reactions and strategic planning, tailoring it to the specific demands of the task at hand. Extensive experiments and real-world applications in multi-robot systems showcase our framework’s superior performance, marking significant advancements over baselines.

Behavioral cloning from human demonstrations has succeeded in programming a robot to generate fine-grained motion, but it is still challenging to learn multimodal trajectories such as with various speeds. This restricts the use of a robot dataset collected by multiusers because the different proficiency of robot operators makes the dataset have diverse distributions of speed. To tackle this issue, we develop Hierarchical Action Chunking Transformer with Vector-quantization (HACT-Vq) to efficiently learn temporal multimodality in addition to fine-grained motion. The proposed hierarchical model consists of a high-level policy to make planning for a latent subgoal and style, and a low-level policy to predict an action chunk conditioned with the latent subgoal and style. The latent subgoal and style are trained as discrete representations so that high-level policy can efficiently learn multimodal distributions of demonstrations and retrieve the mode of fast behavior. In experiments, we set up bimanual robots in both simulation and real-world environments, and collected demonstrations with various speeds. The proposed model with the quantized subgoal and style showed the highest success rates with fast imitation behavior. Our code is available at https://github.com/SamsungLabs/hierarchical-act.

This work presents HiLMa-Res, a hierarchical framework leveraging reinforcement learning to tackle manipulation tasks while performing continuous locomotion using quadrupedal robots. Unlike most previous efforts that focus on solving a specific task, HiLMa-Res is designed to be general for various loco-manipulation tasks that require quadrupedal robots to maintain sustained mobility. The novel design of this framework tackles the challenges of integrating continuous locomotion control and manipulation using legs. It develops an operational space locomotion controller that can track arbitrary robot end-effector (toe) trajectories while walking at different velocities. This controller is designed to be generic to different downstream tasks, and therefore, can be utilized in high-level manipulation planning policy to address specific tasks. To demonstrate the versatility of this framework, we utilize HiLMa-Res to tackle several challenging loco-manipulation tasks using a quadrupedal robot in the real world. These tasks span from leveraging state-based policy to vision-based policy, from training purely from the simulation data to learning from real-world data. In these tasks, HiLMa-Res shows better performance than other methods.

Efficient and scalable adaptive traffic signal control is crucial in reducing congestion, maximizing through-put, and improving mobility experience in ever-expanding cities. Recent advances in multi-agent reinforcement learning (MARL) with parameter sharing have significantly improved the adaptive optimization of large-scale, complex, and dynamic traffic flows. However, the limited model representation capability due to shared parameters impedes the learning of diverse control strategies for intersections with different flows/topologies, posing significant challenges to achieving effective signal control in complex and varied real-world traffic scenarios. To address these challenges, we present a novel MARL-based general traffic signal control framework, called HeteroLight. Specifically, we first introduce a General Feature Extraction (GFE) module, crafted in a decoder-only fashion, where we employ an attention mechanism to facilitate efficient and flexible extraction of traffic dynamics at intersections with varied topologies. Additionally, we incorporate an Intersection Specifics Extraction (ISE) module, designed to identify key latent vectors that represent the unique intersection’s topology and traffic dynamics through variational inference techniques. By integrating the learned intersection-specific information into policy learning, we enhance the parameter-sharing mechanism, improving the model’s representation diversity among different agents and enabling the learning of a more efficient shared control strategy. Through comprehensive evaluations against other state-of-the-art traffic signal control methods on the real-world Monaco traffic network, our empirical findings reveal that HeteroLight consistently outperforms other methods across various evaluation metrics, highlighting its superiority in optimizing traffic flows in heterogeneous traffic networks.