IROS 2024 论文列表

This paper reports the design, simulation, and experiment of a robotic leg prototype named Cury, which has the potential to achieve minimal clearance and excellent backdrivability. Inspired by human walking data, the actuator design incorporates four-bar linkages and ball screws and is further optimized to meet the torque requirement. The Webots simulation is used to obtain the closed-loop chain description of the robotic leg from fits the URDF specification, and this simulation is used to assess the actuator output requirements at a given predefined trajectory. Leveraging customized ac motors and drives, Cury demonstrates satisfactory trajectory tracking performance using a simple controller. The motor drive design files and Webots simulation files are open-sourced.

Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decision transformer (DT) architecture has shown promise across various domains. However, despite its initial success, DTs have underperformed on several challenging datasets in goal-conditioned RL. This limitation stems from the inefficiency of return conditioning for guiding policy learning, particularly in unstructured and suboptimal datasets, resulting in DTs failing to effectively learn temporal compositionality. Moreover, this problem might be further exacerbated in long-horizon sparse-reward tasks. To address this challenge, we propose the Predictive Coding for Decision Transformer (PCDT) framework, which leverages generalized future conditioning to enhance DT methods. PCDT utilizes an architecture that extends the DT framework, conditioned on predictive codings, enabling decision-making based on both past and future factors, thereby improving generalization. Through extensive experiments on eight datasets from the AntMaze and FrankaKitchen environments, our proposed method achieves performance on par with or surpassing existing popular value-based and transformer-based methods in offline goal-conditioned RL. Furthermore, we also evaluate our method on a goal-reaching task with a physical robot.

Cooperating autonomous underwater vehicles (AUVs) often rely on acoustic communication to coordinate their actions effectively. However, the reliability of underwater acoustic communication decreases as the communication range between vehicles increases. Consequently, teams of cooperating AUVs typically make conservative assumptions about the maximum range at which they can communicate reliably. To address this limitation, we propose a novel approach that involves learning a map representing the probability of successful communication based on the locations of the transmitting and receiving vehicles. This probabilistic communication map accounts for factors such as the range between vehicles, environmental noise, and multi-path effects at a given location. In pursuit of this goal, we investigate the application of Gaussian process binary classification to generate the desired communication map. We specialize existing results to this specific binary classification problem and explore methods to incorporate uncertainty in vehicle location into the mapping process. Furthermore, we compare the prediction performance of the probability communication map generated using binary classification with that of a signal-to-noise ratio (SNR) communication map generated using Gaussian process regression. Our approach is experimentally validated using communication and navigation data collected during trials with a pair of Virginia Tech 690 AUVs.

Long-term human trajectory prediction is a challenging yet critical task in robotics and autonomous systems. Prior work that studied how to predict accurate short-term human trajectories with only unimodal features often failed in long-term prediction. Reinforcement learning provides a good solution for learning human long-term behaviors but can suffer from challenges in data efficiency and optimization. In this work, we propose a long-term human trajectory forecasting framework that leverages a guided diffusion model to generate diverse long-term human behaviors in a high-level latent action space, obtained via a hierarchical action quantization scheme using a VQ-VAE to discretize continuous trajectories and the available context. The latent actions are predicted by our guided diffusion model, which uses physics-inspired guidance at test time to constrain generated multimodal action distributions. Specifically, we use reachability analysis during the reverse denoising process to guide the diffusion steps toward physically feasible latent actions. We evaluate our framework on two publicly available human trajectory forecasting datasets: SFU-Store-Nav and JRDB, and extensive experimental results show that our framework achieves superior performance in long-term human trajectory forecasting.

Soft continuum robots, characterized by their inherent compliance and dexterity, are increasingly pivotal in applications requiring delicate interactions with the environment such as the medical field. Despite their advantages, challenges persist in accurately modeling and controlling their shape during interactions with surrounding objects. This is because of the difficulty in modeling the large degrees of freedom in soft-bodied objects that become more active during interactions. In this study, we present a deep visual model to predict the interaction shapes of a soft continuum robot in contact with surrounding objects. By formulating this task as a forward-statics problem, the model uses the initial state images containing the object configuration and future actuation values to predict interactive state images of the robot under this actuation condition. We developed and tested the model in both simulated and physical environments, explored the model’s predictive capabilities using monocular and binocular views, and tested the model’s generalization ability on different datasets. Our results show that deep learning methods are a promising tool for solving the complex problem of predicting the shape of a soft continuum robot interacting with the environment, requiring no prior knowledge about the system dynamics and explicit mapping of the environment. This study paves the way for future explorations in robot-environment interaction modeling and the development of more adaptable interaction shape control strategies.

Micro well-plates are an apparatus commonly used in chemical and biological experiments that are a few centimeters thick and contain wells or divets. In this paper, we aim to solve the task of placing the well-plate onto a well-plate holder (referred to as holder). This task is challenging due to the holder’s raised grooves being a few millimeters in height, with a clearance of less than 1 mm between the well-plate and holder, thus requiring precise control during placing. Our placing task has the following challenges: 1) The holder’s detected pose is uncertain; 2) the required accuracy is at the millimeter to sub-millimeter level due to the raised groove’s shallow height and small clearance; 3) the holder is not fixed to a desk and is susceptible to movement from external forces. To address these challenges, we developed methods including a) using tactile sensors for accurate pose estimation of the grasped well-plate to handle issue (1); b) sliding the well-plate onto the target holder while maintaining contact with the holder’s groove and estimating its orientation for accurate alignment. This allows for high precision control (addressing issue (2)) and prevents displacement of the holder during placement (addressing issue (3)). We demonstrate a high success rate for the well-plate placing task, even under noisy observation of the holder’s pose. 4

In this paper, we propose a novel coarse-to-fine continuous pose diffusion method to enhance the precision of pick-and-place operations within robotic manipulation tasks. Leveraging the capabilities of diffusion networks, we facilitate the accurate perception of object poses. This accurate perception enhances both pick-and-place success rates and overall manipulation precision. Our methodology utilizes a top-down RGB image projected from an RGB-D camera and adopts a coarse-to-fine architecture. This architecture enables efficient learning of coarse and fine models. A distinguishing feature of our approach is its focus on continuous pose estimation, which enables more precise object manipulation, particularly concerning rotational angles. In addition, we employ pose and color augmentation techniques to enable effective training with limited data. Through extensive experiments in simulated and real-world scenarios, as well as an ablation study, we comprehensively evaluate our proposed methodology. Taken together, the findings validate its effectiveness in achieving high-precision pick-and-place tasks.

Robotic manipulation with two-finger grippers is challenged by objects lacking distinct graspable features. Traditional pre-grasping methods, which typically involve repositioning objects or utilizing external aids like table edges, are limited in their adaptability across different object categories and environments. To overcome these limitations, we introduce PreAfford, a novel pre-grasping planning framework incorporating a point-level affordance representation and a relay training approach. Our method significantly improves adaptability, allowing effective manipulation across a wide range of environments and object types. When evaluated on the ShapeNet-v2 dataset, PreAfford not only enhances grasping success rates by 69% but also demonstrates its practicality through successful real-world experiments. These improvements highlight PreAfford’s potential to redefine standards for robotic handling of complex manipulation tasks in diverse settings.

Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim to tackle the challenge of learning general trajectory forecasting representations under limited data availability. We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. The solution is composed of two parts: firstly, we adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. Specifically, we apply vector transformations to reshape the maps, and then employ a rule-based model to generate trajectories on both original and augmented scenes; thus enlarging the driving data without collecting additional real ones. To foster the learning of general representations within this augmented dataset, we comprehensively explore the different pre-training strategies, including extending the concept of a Masked AutoEncoder (MAE) for trajectory forecasting. Without bells and whistles, our proposed pipeline-level solution is general, simple, yet effective: we conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies, which outperform the baseline prediction model by large margins, e.g. 5.04%, 3.84% and 8.30% in terms of MR6, minADE6 and minFDE6. The pre-training dataset and the codes for pre-training and fine-tuning are released at https://github.com/yhli123/Pretraining_on_Synthetic_Driving_Data_for_Trajectory_Prediction.

This paper presents a practical framework for path representation and following control for mobile industrial robots. Mobile industrial robots perform various missions, such as navigating predefined routes and transporting cargo in industrial environments. Unlike traditional AGVs that rely on physical tapes installed densely along routes, our framework supports the generation of drivable paths by connecting waypoints specified by users. The proposed framework generates drivable work paths while considering the permissible deviation between waypoints and the path, as well as the maximum curvature, without nonlinear optimization techniques. Additionally, we introduce a "stopover" attribute for each waypoint to enhance usability in narrow workspaces. Furthermore, we have developed a practical path following control system that takes into account real-world challenges such as actuation delay and computational efficiency. The proposed speed planner incorporates predictive information without relying on optimization techniques, and supports robust following performance by braking intervention if path deviation increases. The effectiveness of the proposed framework has been validated through robot tests, demonstrating accurate path following performance and efficient computation.

This paper tackles the complex task of routing elastic deformable linear objects (DLOs) characterized by considerable stiffness, such as cables or hoses, which are already constrained at both ends. Specifically, a single arm robot is controlled to slide along the unknown contour of the cable, performing collision-free contour following, and to insert specific DLO segments into intermediate known clips. The contour following motion is executed avoiding both collisions with static obstacles and excessive deformation of the manipulated DLO. In particular, the path is defined considering an artificial potential field that is updated after each sliding motion along the DLO. This field accounts for static obstacles, the local cable shape (reconstructed using tactile sensors on the gripper fingertips) and the estimation of the global DLO shape obtained from a dynamic model of the DLO, accounting for the constraints imposed by the clips and the gripper. The proposed method is experimentally validated on an industrial robot executing cable routing in several DLO configurations.

This paper introduces a position control system for a motion stage driven by a low-energy C-core reluctance actuator. The central concept explored here is the utilization of a variable air gap to enable energy-efficient operation of the motion stage. First, we show the design and mathematical model of the reluctance-actuated motion system (RAMS). Then, by analyzing open-loop responses of the RAMS under various conditions including variable air gaps and different excitation voltages, we show that using variable air gap can reduce the required current. Finally, the paper formulates a control approach that combines a feedforward controller to linearize the RAMS’s dynamic behavior and a state feedback controller to achieve tracking performance. Experimental results demonstrate the effectiveness of this control approach in achieving tracking objectives with errors that are less than 2% for constant desired displacement and less than 10% for tracking a sinusoidal reference signal.

It is common in pose graph optimization (PGO) algorithms to assume that noise in the translations and rotations of relative pose measurements is uncorrelated. However, existing work shows that in practice these measurements can be highly correlated, which leads to degradation in the accuracy of PGO solutions that rely on this assumption. Therefore, in this paper we develop a novel algorithm derived from a realistic, correlated model of relative pose uncertainty, and we quantify the resulting improvement in the accuracy of the solutions we obtain relative to state-of-the-art PGO algorithms. Our approach utilizes Riemannian optimization on the planar unit dual quaternion (PUDQ) manifold, and we prove that it converges to first-order stationary points of a Lie-theoretic maximum likelihood objective. Then we show experimentally that, compared to state-of-the-art PGO algorithms, this algorithm produces estimation errors that are lower by 10% to 25% across several orders of magnitude of correlated noise levels and graph sizes.

Visual place recognition (VPR) is a challenging issue for robotics and autonomous systems, focusing on utilizing visual information for robot localization. Currently, hierarchical architecture is being employed by growing works, which embraces RANSAC-based geometric verification for re-ranking. However, RANSAC is time-consuming and only employs geometric information while neglecting other potential information that could be useful for re-ranking. Here we propose a fast position consistency via local patch (PCLP) algorithm to take the position of task-relevant patch-descriptor into account. Without training, it only costs little time but performs better than other re-ranking methods that rely on geometric consistency verification. In this paper, we present a unified place recognition framework that incorporates an aggregation module to extract global features for retrieval and a PCLP validation module to filter local patch for reranking. Meanwhile, we propose a RANSAC-based tightly coupled learning (R-TCL) strategy to discover the best positive sample for training robust models. Unlike common sample mining methods, we introduce RANSAC into the sample mining process, achieving trade-off between efficiency and accuracy. Due to improved positive sample mining strategy and novel position validation module, our model is named as Pos2VPR. Remarkably, Pos2VPR outperforms state-of-the-art methods on four major datasets with extremely short running time.

Femoral artery access is a common and critical procedure for various cardiovascular interventions. Although it is a time critical operation, accessing the Common Femoral Artery (CFA) typically requires expertise found in specialized medical settings. The necessity for specialized personnel or transport to equipped facilities can lead to delays, potentially exacerbating patient outcomes. To address this challenge, a portable and cost-effective robotic device that autonomously localizes a CFA and precisely positions a needle guide is developed. Through the needle guide, needle can be quickly and accurately inserted into the artery even by non-specialist physicians. Different from the conventional B-mode ultrasound guided procedure, the proposed robotic solution utilizes a Doppler transducer for detecting the arterial location and employs a single M-mode transducer for depth measurement. A series of experiments are designed and conducted to validate the system’s feasibility, achieving high accuracy within 2 mm, rapid processing within 1.5 min, and a 100% success rate, thus proving the system’s efficacy. These results convince us for further refinement of the system and support its evaluation in animal studies.

The study addresses the foundational and challenging task of peg-in-hole assembly in robotics, where misalignments caused by sensor inaccuracies and mechanical errors often result in insertion failures or jamming. This research introduces PolyFit, representing a paradigm shift by transitioning from a reinforcement learning approach to a supervised learning methodology. PolyFit is a Force/Torque (F/T)-based supervised learning framework designed for 5-DoF peg-in-hole assembly. It utilizes F/T data for accurate extrinsic pose estimation and adjusts the peg pose to rectify misalignments. Extensive training in a simulated environment involves a dataset encompassing a diverse range of peg-hole shapes, extrinsic poses, and their corresponding contact F/T readings. The study proposes a sim-to-real adaptation method for real-world application, using a sim-real paired dataset to enable effective generalization to complex and unseen polygon shapes. Real-world evaluations demonstrate substantial success rates of 96.7% and 91.3%, highlighting the robustness and adaptability of the proposed method. Videos of data generation and experiments are available online at https://sites.google.com/view/polyfit-peginhole.

This paper investigates the task of the open-ended interactive robotic manipulation on table-top scenarios. While recent Large Language Models (LLMs) enhance robots' comprehension of user instructions, their lack of visual grounding constrains their ability to physically interact with the environment. This is because the robot needs to locate the target object for manipulation within the physical workspace. To this end, we introduce an interactive robotic manipulation framework called Polaris, which integrates perception and interaction by utilizing GPT-4 alongside grounded vision models. For precise manipulation, it is essential that such grounded vision models produce detailed object pose for the target object, rather than merely identifying pixels belonging to them in the image. Consequently, we propose a novel Synthetic-to-Real (Syn2Real) pose estimation pipeline. This pipeline utilizes rendered synthetic data for training and is then transferred to real-world manipulation tasks. The real-world performance demonstrates the efficacy of our proposed pipeline and underscores its potential for extension to more general categories. Moreover, real-robot experiments have showcased the impressive performance of our framework in grasping and executing multiple manipulation tasks. This indicates its potential to generalize to scenarios beyond the tabletop. More information and video results are available here: https://star-uu-wang.github.io/Polaris/.

Exploration of various applications is the frontier of research on inflatable robots. We proposed an articulated robots consisting of multiple pneumatic bladder links connected by rolling contact joints called Hillberry joints. The bladder link is made of a double-layered structure of tarpaulin sheet and polyurethane sheet, which is both airtight and flexible in shape. The integration of the Hilberry joint into an inflatable robot is also a new approach. The rolling contact joint allows wide range of motion of ±150°, the largest among the conventional inflatable joints. Using the proposed mechanism for inflatable robots, we demonstrated moving a 500 g payload with a 3-DoF arm and lifting 3.4 kg and 5 kg payloads with 2-DoF and 1-DoF arms, respectively. We also experimented with a single 3-DoF inflatable leg attached to a dolly to show that the proposed structure worked for legged locomotion.

Recent years have seen autonomous robots deployed in long-term missions across an ever-increasing breadth of domains. We consider robots deployed over a sequence of finite-horizon missions in the same environment, with the objective of maximising the value from observations of some unknown spatiotemporal process. This work is motivated by applications such as ecological monitoring, in which a robot might be repeatedly deployed in the field over weeks or months with the task of modelling processes of scientific interest. We formalise the problem of long-term monitoring over multiple finite-horizon missions as a Markov decision process with a partially unknown state, and present an online planning approach to address it. Our approach uses a spatiotemporal Gaussian process to model the environment and make predictions about unvisited states, integrating this with a belief-based Monte Carlo tree search algorithm which decides where the robot should go next. We demonstrate the strengths of our framework empirically through a series of experiments using synthetic data as well as real acoustic data from monitoring of bioactivity in coral reefs.