ICRA 2024 Papers

In the natural world, insects exhibit remarkable locomotion capabilities through a combination of running and jumping. However, replicating this versatile locomotion in a soft robot poses technical and design complexities. Here, we propose a dynamic soft robot named LeapRun that possesses agile locomotion and the ability to perform continuous jumping. To achieve this, a prototype soft robot (weight of 300 mg, size of 30 mm × 15 mm × 5 mm), composed of piezoelectric thin film, shape memory alloy, magnet-locking mechanism, and corresponding support structures, is fabricated. Experimental results demonstrate a maximum moving speed of 15 cm/s and a maximum jumping height of 8.7 cm. Continuous jumping of steps and crossing of complex rugged surfaces are realized. Besides, integrated with the power source, wireless communication module, and control module, the untethered operation is also presented, showcasing the potential for multiple applications in search and rescue, exploration, and monitoring.

Fiducial markers enable reliable service robot control. In human-robot coexistence environments, efficient placement of square or circular markers can be challenging due to limited space. In this study, we developed a world-first, elongated fiducial marker, capable of high-accuracy 6-DoF measurements, designed to be installable in tight spaces. We introduced two types of lenticular angle gauges to enhance pose estimation and developed new marker patterns and measurement algorithms to maintain recognition distance and accuracy. The proposed marker achieved a measurement accuracy of 0.1% position error and 0.5° orientation error. This technology will enhance the practicality and applicability of fiducial markers, contributing to the creation of robot-friendly space for future service robots.

This paper presents an insole-type sensor module with a novel leaf-inspired force-sensitive resistor (FSR) array for accurate three-dimensional ground reaction force (GRF) estimation during human’s various motions. Joint torque analysis, essential for numerous applications in biomechanics and wearable robotics, necessitates the measurement of three-dimensional GRF vector information, traditionally achieved in indoor environments using costly force plates. To overcome these limitations, this study proposes an alternative method by incorporating FSRs on three inclined planes within the insole. A vector scaling process transforms the force values from the FSRs into the three-dimensional force vector, enabling continuous and user-independent estimation of GRF. The sensor module is integrated with machine learning, demonstrating its accuracy and usability in various motion scenarios. The results confirm the effectiveness of the leaf-inspired FSR array, giving the possibilities for portable and cost-effective motion analysis systems.

Language-guided active sensing is a robotics sub-task where a robot with an onboard sensor interacts efficiently with the environment via object manipulation to maximize perceptual information, following given language instructions. These tasks appear in various practical robotics applications, such as household service, search and rescue, and environment monitoring. Despite many applications, the existing works do not account for language instructions and have mainly focused on surface sensing, i.e., perceiving the environment from the outside without rearranging it for dense sensing. Therefore, in this paper, we introduce the first language-guided active sensing approach that allows users to observe specific parts of the environment via object manipulation. Our method spatially associates the environment with language instructions, determines the best camera viewpoints for perception, and then iteratively selects and relocates the best view-blocking objects to provide the dense perception of the region of interest. We evaluate our method against different baseline algorithms in simulation and also demonstrate it in real-world confined cabinet-like settings with multiple unknown objects. Our results show that the proposed method exhibits better performance across different metrics and successfully generalizes to real-world complex scenarios.

Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this work, we introduce LEXIS, a real-time indoor Simultaneous Localization and Mapping (SLAM) system that harnesses the open-vocabulary nature of Large Language Models (LLMs) to create a unified approach to scene understanding and place recognition. The approach first builds a topological SLAM graph of the environment (using visual-inertial odometry) and embeds Contrastive Language-Image Pretraining (CLIP) features in the graph nodes. We use this representation for flexible room classification and segmentation, serving as a basis for room-centric place recognition. This allows loop closure searches to be directed towards semantically relevant places. Our proposed system is evaluated using both public, simulated data and real-world data, covering office and home environments. It successfully categorizes rooms with varying layouts and dimensions and outperforms the state-of-the-art (SOTA). For place recognition and trajectory estimation tasks we achieve equivalent performance to the SOTA, all also utilizing the same pre-trained model. Lastly, we demonstrate the system’s potential for planning. Video at: https://youtu.be/gRqF3euDfX8

The language-conditioned robotic manipulation aims to transfer natural language instructions into executable actions, from simple "pick-and-place" to tasks requiring intent recognition and visual reasoning. Inspired by the dual-process theory in cognitive science—which suggests two parallel systems of fast and slow thinking in human decision-making—we introduce Robotics with Fast and Slow Thinking (RFST), a framework that mimics human cognitive architecture to classify tasks and makes decisions on two systems based on instruction types. Our RFST consists of two key components: 1) an instruction discriminator to determine which system should be activated based on the current user’s instruction, and 2) a slow-thinking system that is comprised of a fine-tuned vision-language model aligned with the policy networks, which allow the robot to recognize user’s intention or perform reasoning tasks. To assess our methodology, we built a dataset featuring real-world trajectories, capturing actions ranging from spontaneous impulses to tasks requiring deliberate contemplation. Our results, both in simulation and real-world scenarios, confirm that our approach adeptly manages intricate tasks that demand intent recognition and reasoning.

Affordance detection and pose estimation are of great importance in many robotic applications. Their combination helps the robot gain an enhanced manipulation capability, in which the generated pose can facilitate the corresponding affordance task. Previous methods for affodance-pose joint learning are limited to a predefined set of affordances, thus limiting the adaptability of robots in real-world environments. In this paper, we propose a new method for language-conditioned affordance-pose joint learning in 3D point clouds. Given a 3D point cloud object, our method detects the affordance region and generates appropriate 6-DoF poses for any unconstrained affordance label. Our method consists of an open-vocabulary affordance detection branch and a language-guided diffusion model that generates 6-DoF poses based on the affordance text. We also introduce a new high-quality dataset for the task of language-driven affordance-pose joint learning. Intensive experimental results demonstrate that our proposed method works effectively on a wide range of open-vocabulary affordances and outperforms other baselines by a large margin. In addition, we illustrate the usefulness of our method in real-world robotic applications. Our code and dataset are publicly available at https://3DAPNet.github.io.

In this paper, a method for generating a map from path information described using natural language (textual path) is proposed. In recent years, robotics research mainly focus on vision-and-language navigation (VLN), a navigation task based on images and textual paths. Although VLN is expected to facilitate user instructions to robots, its current implementation requires users to explain the details of the path for each navigation session, which results in high explanation costs for users. To solve this problem, we proposed a method that creates a map as a topological map from a textual path and automatically creates a new path using this map. We believe that large language models (LLMs) can be used to understand textual path. Therefore, we propose and evaluate two methods, one for storing implicit maps in LLMs, and the other for generating explicit maps using LLMs. The implicit map is in the LLM’s memory. It is created using prompts. In the explicit map, a topological map composed of nodes and edges is constructed and the actions at each node are stored. This makes it possible to estimate the path and actions at waypoints on an undescribed path, if enough information is available. Experimental results on path instructions generated in a real environment demonstrate that generating explicit maps achieves significantly higher accuracy than storing implicit maps in the LLMs.

The socially-aware navigation system has evolved to adeptly avoid various obstacles while performing multiple tasks, such as point-to-point navigation, human-following, and -guiding. However, a prominent gap persists: in Human-Robot Interaction (HRI), the procedure of communicating commands to robots demands intricate mathematical formulations. Furthermore, the transition between tasks does not quite possess the intuitive control and user-centric interactivity that one would desire. In this work, we propose an LLM-driven interactive multimodal multitask robot navigation framework, termed LIM2N, to solve the above new challenge in the navigation field. We achieve this by first introducing a multimodal interaction framework where language and hand-drawn inputs can serve as navigation constraints and control objectives. Next, a reinforcement learning agent is built to handle multiple tasks with the received information. Crucially, LIM2N creates smooth cooperation among the reasoning of multimodal input, multitask planning, and adaptation and processing of the intelligent sensing modules in the complicated system. Detailed experiments are conducted in both simulation and the real world demonstrating that LIM2N has solid user needs understanding, alongside an enhanced interactive experience.

Long-term human motion prediction (LHMP) is essential for safely operating autonomous robots and vehicles in populated environments. It is fundamental for various applications, including motion planning, tracking, human-robot interaction and safety monitoring. However, accurate prediction of human trajectories is challenging due to complex factors, including, for example, social norms and environmental conditions. The influence of such factors can be captured through Maps of Dynamics (MoDs), which encode spatial motion patterns learned from (possibly scattered and partial) past observations of motion in the environment and which can be used for data-efficient, interpretable motion prediction (MoD-LHMP). To address the limitations of prior work, especially regarding accuracy and sensitivity to anomalies in long-term prediction, we propose the Laminar Component Enhanced LHMP approach (LaCE-LHMP). Our approach is inspired by data-driven airflow modelling, which estimates laminar and turbulent flow components and uses predominantly the laminar components to make flow predictions. Based on the hypothesis that human trajectory patterns also manifest laminar flow (that represents predictable motion) and turbulent flow components (that reflect more unpredictable and arbitrary motion), LaCE-LHMP extracts the laminar patterns in human dynamics and uses them for human motion prediction. We demonstrate the superior prediction performance of LaCE-LHMP through benchmark comparisons with state-of-the-art LHMP methods, offering an unconventional perspective and a more intuitive understanding of human movement patterns.

Fusing the camera and LiDAR information in the unified BEV representation serves as the elegant paradigm for the 3D detection tasks. Current multi-modal fusion methods in BEV can be categorized into LSS-based and Transformer-based in terms of their view transformation. The former leverages inaccurate depth prediction and massive pseudo points for perspective-to-BEV transformation while the latter only fetches sparse image features to the BEV representation. To overcome their shortcomings, an optimized view transformation is proposed, which can be easily modulated into the LSS-based methods. The proposed module capitalizes on the LSS mechanism to establish dense associations between perspective pixels and BEV grids. It utilizes the attention mechanism to compute similarity scores for each associated pair during feature aggregation. Starting from the BEVFusion baseline, we further introduce (1) cross-attention within the associated subsets to transfer image features into the BEV, and (2) a multi-scale feature fusion mechanism for LSS-based view transformation. Extensive experiments on nuScenes validate the effectiveness and efficiency of our proposed module, which achieves an increase of 1.3% in mAP compared to the baseline model.

With innovation in fields such as autonomous driving and augmented reality, point cloud-based place recognition has gained significant attention. Many methods try to address this problem by extracting and matching global descriptors in a database, but they often must balance the extraction of comprehensive contextual information and large model sizes. To overcome this challenge, we propose a lightweight parameter-shared network (LPS-Net), which includes multiple bidirectional perception units (BPUs) to extract multiscale long-range contextual information and parameter-shared NetVLADs (PS-VLADs) to aggregate descriptors. A BPU includes a parameter-shared convolution module (SharedConv) that significantly compresses the model and enhances its ability to capture informative features. In PS-VLADs, we replace half the parameters used in the original NetVLAD with trainable scalars, which further reduces the model size, and theoretically prove their equivalence. Experimental results demonstrate that LPS-Net achieves state-of-the-art performance at the task of point cloud-based place recognition while maintaining a small model size. Code and supplementary materials can be found at https://github.com/Yavinr/LPS-Net.

Due to the difficulty of acquiring large-scale 3D human keypoint annotation, previous methods for 3D human pose estimation (HPE) have often relied on 2D image features and sequential 2D annotations. Furthermore, the training of these networks typically assumes the prediction of a human bounding box and the accurate alignment of 3D point clouds with 2D images, making direct application in real-world scenarios challenging. In this paper, we present the 1st framework for end-to-end 3D human pose estimation, named LPFormer, which uses only LiDAR as its input along with its corresponding 3D annotations. LPFormer consists of two stages: firstly, it identifies the human bounding box and extracts multi-level feature representations, and secondly, it utilizes a transformer-based network to predict human keypoints based on these features. Our method demonstrates that 3D HPE can be seamlessly integrated into a strong LiDAR perception network and benefit from the features extracted by the network. Experimental results on the Waymo Open Dataset demonstrate the state-of-the-art performance, and improvements even compared to previous multi-modal solutions.

We introduce LOTUS, a continual imitation learning algorithm that empowers a physical robot to continuously and efficiently learn to solve new manipulation tasks throughout its lifespan. The core idea behind LOTUS is constructing an ever-growing skill library from a sequence of new tasks with a small number of human demonstrations. LOTUS starts with a continual skill discovery process using an open-vocabulary vision model, which extracts skills as recurring patterns presented in unsegmented demonstrations. Continual skill discovery updates existing skills to avoid catastrophic forgetting of previous tasks and adds new skills to solve novel tasks. LOTUS trains a meta-controller that flexibly composes various skills to tackle vision-based manipulation tasks in the lifelong learning process. Our comprehensive experiments show that LOTUS outperforms state-of-the-art baselines by over 11% in success rate, showing its superior knowledge transfer ability compared to prior methods. More results and videos can be found on the project website: https://ut-austin-rpl.github.io/Lotus/.

Climbing robots can investigate scientifically valuable sites that conventional rovers cannot access due to steep terrain features. Robots equipped with microspine grippers are particularly well-suited to ascending rocky cliff faces, but most existing designs are either large and slow or limited to relatively flat surfaces such as walls. We present a novel free-climbing robot to bridge this gap through innovations in gripper design and force control. Fully passive grippers and wrist joints allow secure grasping while reducing mass and complexity. Forces are distributed among the robot’s grippers using an optimization-based control strategy to minimize the risk of unexpected detachment. The robot prototype has demonstrated vertical climbing on both flat cinder block walls and uneven rock surfaces in full Earth gravity.

3D visual grounding is a critical skill for household robots, enabling them to navigate, manipulate objects, and answer questions based on their environment. While existing approaches often rely on extensive labeled data or exhibit limitations in handling complex language queries, we propose LLM-Grounder, a novel zero-shot, open-vocabulary, Large Language Model (LLM)-based 3D visual grounding pipeline. LLM-Grounder utilizes an LLM to decompose complex natural language queries into semantic constituents and employs a visual grounding tool, such as OpenScene or LERF, to identify objects in a 3D scene. The LLM then evaluates the spatial and commonsense relations among the proposed objects to make a final grounding decision. Our method does not require any labeled training data and can generalize to novel 3D scenes and arbitrary text queries. We evaluate LLM-Grounder on the ScanRefer benchmark and demonstrate state-of-the-art zero-shot grounding accuracy. Our findings indicate that LLMs significantly improve the grounding capability, especially for complex language queries, making LLM-Grounder an effective approach for 3D vision-language tasks in robotics.

Large Language Models (LLMs) have been widely utilized to perform complex robotic tasks. However, handling external disturbances during tasks is still an open challenge. This paper proposes a novel method to achieve robotic adaptive tasks based on LLMs and Behavior Trees (BTs). It utilizes ChatGPT to reason the descriptive steps of tasks. In order to enable ChatGPT to understand the environment, semantic maps are constructed by an object recognition algorithm. Then, we design a Parser module based on Bidirectional Encoder Representations from Transformers (BERT) to parse these steps into initial BTs. Subsequently, a BTs Update algorithm is proposed to expand the initial BTs dynamically to control robots to perform adaptive tasks. Different from other LLM-based methods for complex robotic tasks, our method outputs variable BTs that can add and execute new actions according to environmental changes, which is robust to external disturbances. Our method is validated with simulation in different practical scenarios.

Visual question answering (VQA) can be fundamentally crucial for promoting robotic-assisted surgical education. In practice, the needs of trainees are constantly evolving, such as learning more surgical types and adapting to new surgical instruments/techniques. Therefore, continually updating the VQA system by a sequential data stream from multiple resources is demanded in robotic surgery to address new tasks. In surgical scenarios, the privacy issue of patient data often restricts the availability of old data when updating the model, necessitating an exemplar-free continual learning (CL) setup. However, prior studies overlooked two vital problems of the surgical domain: i) large domain shifts from diverse surgical operations collected from multiple departments or clinical centers, and ii) severe data imbalance arising from the uneven presence of surgical instruments or activities during surgical procedures. This paper proposes to address these two problems with a multimodal large language model (LLM) and an adaptive weight assignment methodology. We first develop a new multi-teacher CL framework that leverages a multimodal LLM as the additional teacher. The strong generalization ability of the LLM can bridge the knowledge gap when domain shifts and data imbalances occur. We then put forth a novel data processing method that transforms complex LLM embeddings into logits compatible with our CL framework. We also design an adaptive weight assignment approach that balances the generalization ability of the LLM and the domain expertise of the old CL model. Finally, we construct a new dataset for surgical VQA tasks. Extensive experimental results demonstrate the superiority of our method to other advanced CL models.

Odometry estimation is crucial for every autonomous system requiring navigation in an unknown environment. In modern mobile robots, 3D LiDAR-inertial systems are often used for this task. By fusing LiDAR scans and IMU measurements, these systems can reduce the accumulated drift caused by sequentially registering individual LiDAR scans and provide a robust pose estimate. Although effective, LiDAR-inertial odometry systems require proper parameter tuning to be deployed. In this paper, we propose LIO-EKF, a tightly-coupled LiDAR-inertial odometry system based on point-to-point registration and the classical extended Kalman filter scheme. We propose an adaptive data association that considers the relative pose uncertainty, the map discretization errors, and the LiDAR noise. In this way, we can substantially reduce the parameters to tune for a given type of environment. The experimental evaluation suggests that the proposed system performs on par with the state-of-the-art LiDAR-inertial odometry pipelines but is significantly faster in computing the odometry. The source code of our implementation is publicly available (https://github.com/YibinWu/LIO-EKF).