ICRA 2024 论文列表

Deformable object manipulation presents a unique set of challenges in robotic manipulation by exhibiting high degrees of freedom and severe self-occlusion. Choosing state representations for materials that exhibit plastic behavior, like modeling clay or bread dough, is also difficult because they permanently deform under stress and are constantly changing shape. In this work, we investigate each of these challenges using the task of robotic sculpting with a parallel gripper. We propose a system that uses point clouds as the state representation and leverages a pre-trained point cloud reconstruction transformer to learn a latent dynamics model to predict material deformations given a grasp action. We design a novel action sampling algorithm that reasons about geometrical differences between point clouds to further improve the efficiency of model-based planners. All data and experiments are conducted entirely in the real world. Our experiments show the proposed system is able to successfully capture the dynamics of clay, and is able to create a variety of simple shapes. Videos and additional figures are available on our project page at: https://sites.google.com/andrew.cmu.edu/sculptbot

We present a new reproducible benchmark for evaluating robot manipulation in the real world, specifically focusing on a pick-and-place task. Our benchmark uses the YCB object set, a commonly used dataset in the robotics community, to ensure that our results are comparable to other studies. Additionally, the benchmark is designed to be easily reproducible in the real world, making it accessible to researchers and practitioners. We also provide our experimental results and analyzes for model-based and model-free 6D robotic grasping on the benchmark, where representative algorithms are evaluated for object perception, grasping planning, and motion planning. We believe that our benchmark will be a valuable tool for advancing the field of robot manipulation. By providing a standardized evaluation framework, researchers can more easily compare different techniques and algorithms, leading to faster progress in developing robot manipulation methods. 1

We consider the task of traffic scene generation. A common approach in the self-driving industry is to use manual creation to generate scenes with specific characteristics and automatic generation to generate canonical scenes at scale. However, manual creation is not scalable, and automatic generation typically use rules-based algorithms that lack realism. In this paper, we propose SceneControl, a framework for controllable traffic scene generation. To capture the complexity of real traffic, SceneControl learns an expressive diffusion model from data. Then, using guided sampling, we can flexibly control the sampling process to generate scenes that exhibit desired characteristics. Our experiments show that SceneControl achieves greater realism and controllability than the existing state-of-the-art. We also illustrate how SceneControl can be used as a tool for interactive traffic scene generation.

Navigating complex and dynamic environments requires autonomous vehicles (AVs) to reason about both visible and occluded regions. This involves predicting the future motion of observed agents, inferring occluded ones, and modeling their interactions based on vectorized scene representations of the partially observable environment. However, prior work on occlusion inference and trajectory prediction have developed in isolation, with the former based on simplified rasterized methods and the latter assuming full environment observability. We introduce the Scene Informer, a unified approach for predicting both observed agent trajectories and inferring occlusions in a partially observable setting. It uses a transformer to aggregate various input modalities and facilitate selective queries on occlusions that might intersect with the AV’s planned path. The framework estimates occupancy probabilities and likely trajectories for occlusions, as well as forecast motion for observed agents. We explore common observability assumptions in both domains and their performance impact. Our approach outperforms existing methods in both occupancy prediction and trajectory prediction in partially observable setting on the Waymo Open Motion Dataset. Our implementation with additional visualizations is available at https://github.com/sisl/SceneInformer.

Humans are remarkable in their ability to navigate without metric information. We can read abstract 2D maps, such as floor-plans or hand-drawn sketches, and use them to navigate in unseen rich 3D environments, without requiring prior traversals to map out these scenes in detail. We posit that this is enabled by the ability to represent the environment abstractly as interconnected navigational behaviours, e.g., "follow the corridor" or "turn right", while avoiding detailed, accurate spatial information at the metric level. We introduce the Scene Action Map (SAM), a behavioural topological graph, and propose a learnable map-reading method, which parses a variety of 2D maps into SAMs. Map-reading extracts salient information about navigational behaviours from the overlooked wealth of pre-existing, abstract and inaccurate maps, ranging from floor-plans to sketches. We evaluate the performance of SAMs for navigation, by building and deploying a behavioural navigation stack on a quadrupedal robot. Videos and more information is available at: https://scene-action-maps.github.io.

This paper studies Reinforcement Learning (RL) techniques to enable team coordination behaviors in graph environments with support actions among teammates to reduce the costs of traversing certain risky edges in a centralized manner. While classical approaches can solve this non-standard multi-agent path planning problem by converting the original Environment Graph (EG) into a Joint State Graph (JSG) to implicitly incorporate the support actions, those methods do not scale well to large graphs and teams. To address this curse of dimensionality, we propose to use RL to enable agents to learn such graph traversal and teammate supporting behaviors in a data-driven manner. Specifically, through a new formulation of the team coordination on graphs with risky edges problem into Markov Decision Processes (MDPs) with a novel state and action space, we investigate how RL can solve it in two paradigms: First, we use RL for a team of agents to learn how to coordinate and reach the goal with minimal cost on a single EG. We show that RL efficiently solves problems with up to 20/4 or 25/3 nodes/agents, using a fraction of the time needed for JSG to solve such complex problems; Second, we learn a general RL policy for any N-node EGs to produce efficient supporting behaviors. We present extensive experiments and compare our RL approaches against their classical counterparts.

Robotic manipulation is a key enabler for automation in the fulfillment logistics sector. Such robotic systems require perception and manipulation capabilities to handle a wide variety of objects. Existing systems either operate on a closed set of objects or perform object-agnostic manipulation which lacks the capability for deliberate and reliable manipulation at scale. Object identification (ID) unlocks the ability for large-scale, object-centric manipulation by mapping object segments to one of the previously seen objects from a database. Nevertheless, it is often limited by the availability of reference data or coverage for objects in a database. In this work, we propose to perform object identification with multiple reference databases, including images and text references, each with a different coverage and matching challenge. We propose a training strategy that tackles the challenges of learning domain-invariant image embeddings, image-text matching and fusing predictions from different sources. We perform experiments over a recent benchmark with over 190K+ unique objects, extend the dataset with the additional reference sources and propose an evaluation strategy that simulates coverage for different reference sources. Model trained with the proposed learning pipeline shows robust performance over a range of simulation experiments.

Motion forecasting has become an increasingly critical component of autonomous robotic systems. Onboard compute budgets typically limit the accuracy of real-time systems. In this work we propose methods of improving motion forecasting systems subject to limited compute budgets by combining model ensemble and distillation techniques. The use of ensembles of deep neural networks has been shown to improve generalization accuracy in many application domains. We first demonstrate significant performance gains by creating a large ensemble of optimized single models. We then develop a generalized framework to distill motion forecasting model ensembles into small student models which retain high performance with a fraction of the computing cost. For this study we focus on the task of motion forecasting using real world data from autonomous driving systems. We develop ensemble models that are very competitive on the Waymo Open Motion Dataset (WOMD) and Argoverse leaderboards. From these ensembles, we train distilled student models which have high performance at a fraction of the compute costs. These experiments demonstrate distillation from ensembles as an effective method for improving accuracy of predictive models for robotic systems with limited compute budgets.

We present a scalable combined localization infrastructure deployment and task planning algorithm for underwater assembly. Infrastructure is autonomously modified to suit the needs of manipulation tasks based on an uncertainty model on the infrastructure’s positional accuracy. Our uncertainty model can be combined with the noise characteristics from multiple sensors. For the task planning problem, we propose a layer-based clustering approach that completes the manipulation tasks one cluster at a time. We employ movable visual fiducial markers as infrastructure and an autonomous underwater vehicle (AUV) for manipulation tasks. The proposed task planning algorithm is computationally simple, and we implement it on AUV without any offline computation requirements. Combined hardware experiments and simulations over large datasets show that the proposed technique is scalable to large areas.

A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques, such as in-context learning or re-prompting with state feedback, placing new importance on the token budget for the context window. An under-explored but natural next direction is to investigate LLMs as multi-robot task planners. However, long-horizon, heterogeneous multi-robot planning introduces new challenges of coordination while also pushing up against the limits of context window length. It is therefore critical to find token-efficient LLM planning frameworks that are also able to reason about the complexities of multi-robot coordination. In this work, we compare the task success rate and token efficiency of four multi-agent communication frameworks (centralized, decentralized, and two hybrid) as applied to four coordination-dependent multi-agent 2D task scenarios for increasing numbers of agents. We find that a hybrid framework achieves better task success rates across all four tasks and scales better to more agents. We further demonstrate the hybrid frameworks in 3D simulations where the vision-to-text problem and dynamical errors are considered. See our project website 4 for prompts, videos, and code.

We propose a novel angular velocity estimation method to increase the robustness of Simultaneous Localization And Mapping (SLAM) algorithms against gyroscope saturations induced by aggressive motions. Field robotics expose robots to various hazards, including steep terrains, landslides, and staircases, where substantial accelerations and angular velocities can occur if the robot loses stability and tumbles. These extreme motions can saturate sensor measurements, especially gyroscopes, which are the first sensors to become inoperative. While the structural integrity of the robot is at risk, the robustness of the SLAM framework is oftentimes given little consideration. Consequently, even if the robot is physically capable of continuing the mission, its operation will be compromised due to a corrupted representation of the world. Regarding this problem, we propose a method to estimate the angular velocity using accelerometers during extreme rotations caused by tumbling. We show that our method reduces the median localization error by 71.5 % in translation and 65.5 % in rotation and is robust to mapping failures, which occurred in 37.5 % of the experiments without our method. We also propose the Tumbling-Induced Gyroscope Saturation (TIGS) dataset, which consists of outdoor experiments recording the motion of a mechanical lidar subject to angular velocities four times higher than other similar datasets available. The dataset is available online at https://github.com/norlab-ulaval/Norlab_wiki/wiki/TIGS-Dataset.

Motivated by the challenge of achieving rapid learning in physical environments, this paper presents the development and training of a robotic system designed to navigate and solve a labyrinth game using model-based reinforcement learning techniques. The method involves extracting low-dimensional observations from camera images, along with a cropped and rectified image patch centered on the current position within the labyrinth, providing valuable information about the labyrinth layout. The learning of a control policy is performed purely on the physical system using model-based reinforcement learning, where the progress along the labyrinth’s path serves as a reward signal. Additionally, we exploit the system’s inherent symmetries to augment the training data. Consequently, our approach learns to successfully solve a popular real-world labyrinth game in record time, with only 5 hours of real-world training data.

In urban environments for delivery robots, particularly in areas such as campuses and towns, many custom features defy standard road semantic categorizations. Addressing this challenge, our paper introduces a method leveraging Salient Object Detection (SOD) to extract these unique features, employing them as pivotal factors for enhanced robot loop closure and localization. Traditional geometric feature-based localization is hampered by fluctuating illumination and appearance changes. Our preference for SOD over semantic segmentation sidesteps the intricacies of classifying a myriad of non-standardized urban features. To achieve consistent ground features, the Motion Compensate IPM (MC-IPM) technique is implemented, capitalizing on motion for distortion compensation and subsequently selecting the most pertinent salient ground features through moment computations. For thorough evaluation, we validated the saliency detection and localization performances to the real urban scenarios. Project page: https://sites.google.com/view/salient-ground-feature/home.

This paper presents a safety-critical control framework tailored for quadruped robots equipped with a roller arm, particularly when performing locomotive tasks such as autonomous robotic inspection in complex, multi-tiered environments. In this study, we consider the problem of operating a quadrupedal robot in distillation columns, locomoting on column trays and transitioning between these trays with a roller arm. To address this problem, our framework encompasses the following key elements: 1) Trajectory generation for seamless transitions between columns, 2) Foothold re-planning in regions deemed unsafe, 3) Safety-critical control incorporating control barrier functions, 4) Gait transitions based on safety levels, and 5) A low-level controller. Our comprehensive framework, comprising these components, enables autonomous and safe locomotion across multiple layers. We incorporate reduced-order and full-body models to ensure safety, integrating safety-critical control and footstep re-planning approaches. We validate the effectiveness of our proposed framework through practical experiments involving a quadruped robot equipped with a roller arm, successfully navigating and transitioning between different levels within the column tray structure.

Generating safety-critical scenarios is essential for testing and verifying the safety of autonomous vehicles. Traditional optimization techniques suffer from the curse of dimensionality and limit the search space to fixed parameter spaces. To address these challenges, we propose a deep reinforcement learning approach that generates scenarios by sequential editing, such as adding new agents or modifying the trajectories of the existing agents. Our framework employs a reward function consisting of both risk and plausibility objectives. The plausibility objective leverages generative models, such as a variational autoencoder, to learn the likelihood of the generated parameters from the training datasets; It penalizes the generation of unlikely scenarios. Our approach overcomes the dimensionality challenge and explores a wide range of safety-critical scenarios. Our evaluation demonstrates that the proposed method generates safety-critical scenarios of higher quality compared with previous approaches.

This paper presents a safety-critical approach to the coordination of robots in dynamic environments. To this end, we leverage control barrier functions (CBFs) with the forward reachable set to guarantee the safe coordination of the robots while preserving a desired trajectory via a layered controller. The top-level planner generates a safety-ensured trajectory for each agent, accounting for the dynamic constraints in the environment. This planner leverages high-order CBFs based on the forward reachable set to ensure safety-critical coordination control, i.e., guarantee the safe coordination of the robots during locomotion. The middle-level trajectory planner employs single rigid body (SRB) dynamics to generate optimal ground reaction forces (GRFs) to track the safety-ensured trajectories from the top-level planner. The whole-body motions to adhere to the optimal GRFs while ensuring the friction cone condition at the end of each stance leg are generated from the low-level controller. The effectiveness of the approach is demonstrated through simulation and hardware experiments.

Pushing tasks performed by aerial manipulators can be used for contact-based industrial inspections. Underactuated aerial vehicles are widely employed in aerial manipulation due to their widespread availability and relatively low cost. Industrial infrastructures often consist of diverse oriented work surfaces. When interacting with such surfaces, the coupled gravity compensation and interaction force generation of underactuated aerial vehicles can present the potential challenge of near-saturation operations. The blind utilization of these platforms for such tasks can lead to instability and accidents, creating unsafe operating conditions and potentially damaging the platform. In order to ensure safe pushing on these surfaces while managing platform saturation, this work establishes a safety assessment process. This process involves the prediction of the saturation level of each actuator during pushing across variable surface orientations. Furthermore, the assessment results are used to plan and execute physical experiments, ensuring safe operations and preventing platform damage.

In this paper, we consider the problem of safety analysis of a closed-loop control system with anytime perception sensor. We formalize the framework and present a general procedure for safety analysis using reachable set computation. We instantiate the procedure for two concrete classes, namely, the classical discrete-time linear system with linear state feedback controller and an extension with variable update rates. We present an exact computational method based on polyhedral manipulations for the first class and an overapproximate method for the second class. Our experimental results demonstrate the feasibility of the approach.

Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints in the process of decision-making and exploration during trial and error. In this paper, a novel model-free Safe RL algorithm, formulated based on the multi-objective policy optimization framework is introduced where the policy is optimized towards optimality and safety, simultaneously. The optimality is achieved by the environment reward function that is subsequently shaped using a safety critic. The advantage of the Safety Optimized RL (SORL) algorithm compared to the traditional Safe RL algorithms is that it omits the need to constrain the policy search space. This allows SORL to find a natural tradeoff between safety and optimality without compromising the performance in terms of either safety or optimality due to strict search space constraints. Through our theoretical analysis of SORL, we propose a condition for SORL’s converged policy to guarantee safety and then use it to introduce an aggressiveness parameter that allows for fine-tuning the mentioned tradeoff. The experimental results obtained in seven different robotic environments indicate a considerable reduction in the number of safety violations along with higher, or competitive, policy returns, in comparison to six different state-of-the-art Safe RL methods. The results demonstrate the significant superiority of the proposed SORL algorithm in safety-critical applications.