OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data

This work presents OVIR-3D, a straightforward yet effective method for open-vocabulary 3D object instance retrieval without using any 3D data for training. Given a language query, the proposed method is able to return a ranked set of 3D object instance segments based on the feature similarity of the instance and the text query. This is achieved by a multi-view fusion of text-aligned 2D region proposals into 3D space, where the 2D region proposal network could leverage 2D datasets, which are more accessible and typically larger than 3D datasets. The proposed fusion process is efficient as it can be performed in real-time for most indoor 3D scenes and does not require additional training in 3D space. Experiments on public datasets and a real robot show the effectiveness of the method and its potential for applications in robot navigation and manipulation.

Socially Cognizant Robotics for a Technology Enhanced Society

Emerging applications of robotics, and concerns about their impact, require the research community to put human-centric objectives front-and-center. To meet this challenge, we advocate an interdisciplinary approach, socially cognizant robotics, which synthesizes technical and social science methods. We argue that this approach follows from the need to empower stakeholder participation (from synchronous human feedback to asynchronous societal assessment) in shaping AI-driven robot behavior at all levels, and leads to a range of novel research perspectives and problems both for improving robots' interactions with individuals and impacts on society. Drawing on these arguments, we develop best practices for socially cognizant robot design that balance traditional technology-based metrics (e.g. efficiency, precision and accuracy) with critically important, albeit challenging to measure, human and society-based metrics.

Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs

We present an Open-Vocabulary 3D Scene Graph (OVSG), a formal framework for grounding a variety of entities, such as object instances, agents, and regions, with free-form text-based queries. Unlike conventional semantic-based object localization approaches, our system facilitates context-aware entity localization, allowing for queries such as ``pick up a cup on a kitchen table" or ``navigate to a sofa on which someone is sitting". In contrast to existing research on 3D scene graphs, OVSG supports free-form text input and open-vocabulary querying. Through a series of comparative experiments using the ScanNet dataset and a self-collected dataset, we demonstrate that our proposed approach significantly surpasses the performance of previous semantic-based localization techniques. Moreover, we highlight the practical application of OVSG in real-world robot navigation and manipulation experiments.

Pick Planning Strategies for Large-Scale Package Manipulation

Automating warehouse operations can reduce logistics overhead costs, ultimately driving down the final price for consumers, increasing the speed of delivery, and enhancing the resiliency to market fluctuations. This extended abstract showcases a large-scale package manipulation from unstructured piles in Amazon Robotics' Robot Induction (Robin) fleet, which is used for picking and singulating up to 6 million packages per day and so far has manipulated over 2 billion packages. It describes the various heuristic methods developed over time and their successor, which utilizes a pick success predictor trained on real production data. To the best of the authors' knowledge, this work is the first large-scale deployment of learned pick quality estimation methods in a real production system.

Large-Scale Package Manipulation via Learned Metrics of Pick Success

Automating warehouse operations can reduce logistics overhead costs, ultimately driving down the final price for consumers, increasing the speed of delivery, and enhancing the resiliency to workforce fluctuations. The past few years have seen increased interest in automating such repeated tasks but mostly in controlled settings. Tasks such as picking objects from unstructured, cluttered piles have only recently become robust enough for large-scale deployment with minimal human intervention. This paper demonstrates a large-scale package manipulation from unstructured piles in Amazon Robotics' Robot Induction (Robin) fleet, which utilizes a pick success predictor trained on real production data. Specifically, the system was trained on over 394K picks. It is used for singulating up to 5~million packages per day and has manipulated over 200~million packages during this paper's evaluation period. The developed learned pick quality measure ranks various pick alternatives in real-time and prioritizes the most promising ones for execution. The pick success predictor aims to estimate from prior experience the success probability of a desired pick by the deployed industrial robotic arms in cluttered scenes containing deformable and rigid objects with partially known properties. It is a shallow machine learning model, which allows us to evaluate which features are most important for the prediction. An online pick ranker leverages the learned success predictor to prioritize the most promising picks for the robotic arm, which are then assessed for collision avoidance. This learned ranking process is demonstrated to overcome the limitations and outperform the performance of manually engineered and heuristic alternatives. To the best of the authors' knowledge, this paper presents the first large-scale deployment of learned pick quality estimation methods in a real production system.

Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos

This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried by a mobile robot. A key feature of the self-supervised training process is a graph-matching algorithm that operates on the over-segmentation output of the point cloud that is reconstructed from each video. The graph matching, along with point cloud registration, is able to find reoccurring object patterns across videos and combine them into 3D object pseudo labels, even under occlusions or different viewing angles. Projected 2D object masks from 3D pseudo labels are used to train a pixel-wise feature extractor through contrastive learning. During online inference, a clustering method uses the learned features to cluster foreground pixels into object segments. Experiments highlight the method's effectiveness on both real and synthetic video datasets, which include cluttered scenes of tabletop objects. The proposed method outperforms existing unsupervised methods for object segmentation by a large margin.

Real2Sim2Real Transfer for Control of Cable-driven Robots via a Differentiable Physics Engine

Tensegrity robots, composed of rigid rods and flexible cables, exhibit high strength-to-weight ratios and extreme deformations, enabling them to navigate unstructured terrain and even survive harsh impacts. However, they are hard to control due to their high dimensionality, complex dynamics, and coupled architecture. Physics-based simulation is one avenue for developing locomotion policies that can then be transferred to real robots, but modeling tensegrity robots is a complex task, so simulations experience a substantial sim2real gap. To address this issue, this paper describes a Real2Sim2Real strategy for tensegrity robots. This strategy is based on a differential physics engine that can be trained given limited data from a real robot (i.e. offline measurements and one random trajectory) and achieve a high enough accuracy to discover transferable locomotion policies. Beyond the overall pipeline, key contributions of this work include computing non-zero gradients at contact points, a loss function, and a trajectory segmentation technique that avoid conflicts in gradient evaluation during training. The proposed pipeline is demonstrated and evaluated on a real 3-bar tensegrity robot.

6N-DoF Pose Tracking for Tensegrity Robots

Tensegrity robots, which are composed of rigid compressive elements (rods) and flexible tensile elements (e.g., cables), have a variety of advantages, including flexibility, light weight, and resistance to mechanical impact. Nevertheless, the hybrid soft-rigid nature of these robots also complicates the ability to localize and track their state. This work aims to address what has been recognized as a grand challenge in this domain, i.e., the pose tracking of tensegrity robots through a markerless, vision-based method, as well as novel, onboard sensors that can measure the length of the robot's cables. In particular, an iterative optimization process is proposed to estimate the 6-DoF poses of each rigid element of a tensegrity robot from an RGB-D video as well as endcap distance measurements from the cable sensors. To ensure the pose estimates of rigid elements are physically feasible, i.e., they are not resulting in collisions between rods or with the environment, physical constraints are introduced during the optimization. Real-world experiments are performed with a 3-bar tensegrity robot, which performs locomotion gaits. Given ground truth data from a motion capture system, the proposed method achieves less than 1 cm translation error and 3 degrees rotation error, which significantly outperforms alternatives. At the same time, the approach can provide pose estimates throughout the robot's motion, while motion capture often fails due to occlusions.

Safe, Occlusion-Aware Manipulation for Online Object Reconstruction in Confined Spaces

Recent work in robotic manipulation focuses on object retrieval in cluttered space under occlusion. Nevertheless, the majority of efforts lack an analysis of conditions for the completeness of the approaches or the methods apply only when objects can be removed from the workspace. This work formulates the general, occlusion-aware manipulation task, and focuses on safe object reconstruction in a confined space with in-place relocation. A framework that ensures safety with completeness guarantees is proposed. Furthermore, an algorithm, which is an instantiation of this framework for monotone instances, is developed and evaluated empirically by comparing against a random and a greedy baseline on randomly generated experiments in simulation. Even for cluttered scenes with realistic objects, the proposed algorithm significantly outperforms the baselines and maintains a high success rate across experimental conditions.

Lazy Rearrangement Planning in Confined Spaces

Object rearrangement is important for many applications but remains challenging, especially in confined spaces, such as shelves, where objects cannot be accessed from above and they block reachability to each other. Such constraints require many motion planning and collision checking calls, which are computationally expensive. In addition, the arrangement space grows exponentially with the number of objects. To address these issues, this work introduces a lazy evaluation framework with a local monotone solver and a global planner. Monotone instances are those that can be solved by moving each object at most once. A key insight is that reachability constraints at the grasps for objects' starts and goals can quickly reveal dependencies between objects without having to execute expensive motion planning queries. Given that, the local solver builds lazily a search tree that respects these reachability constraints without verifying that the arm paths are collision free. It only collision checks when a promising solution is found. If a monotone solution is not found, the non-monotone planner loads the lazy search tree and explores ways to move objects to intermediate locations from where monotone solutions to the goal can be found. Results show that the proposed framework can solve difficult instances in confined spaces with up to 16 objects, which state-of-the-art methods fail to solve. It also solves problems faster than alternatives, when the alternatives find a solution. It also achieves high-quality solutions, i.e., only 1.8 additional actions on average are needed for non-monotone instances.