The COMP ARE Ecosystem aims to improve the compatibility and benchmarking of open-source products for robot manipulation through a series of activities. One such activity is the development of standards and guidelines to specify modularization practices at the component-level for individual modules (e.g., perception, grasp planning, motion planning) and integrations of components that form robot manipulation capabilities at the pipeline-level. This paper briefly reviews our work-in-progress to date to (1) build repositories of open-source products to identify common characteristics of each component in the pipeline, (2) investigate existing modular pipelines to glean best practices, and (3) develop new modular pipelines that advance prior work while abiding by the proposed standards and guidelines.

-- Efficient and safe retrieval of stacked objects in warehouse environments is a significant challenge due to complex spatial dependencies and structural inter-dependencies. Traditional vision-based methods excel at object localization but often lack the physical reasoning required to predict the consequences of extraction, leading to unintended collisions and collapses. This paper proposes a collapse and collision aware grasp planner that integrates dynamic physics simulations for robotic decision-making. Using a single image and depth map, an approximate 3D representation of the scene is reconstructed in a simulation environment, enabling the robot to evaluate different retrieval strategies before execution. Two approaches 1) heuristic-based and 2) physics-based are proposed for both single-box extraction and shelf clearance tasks. Extensive real-world experiments on structured and unstructured box stacks, along with validation using datasets from existing databases, show that our physics-aware method significantly improves efficiency and success rates compared to baseline heuristics. The integration of autonomous robotic systems into warehouse management has led to significant improvements in efficiency, particularly in tasks such as item retrieval, transportation, and inventory organization.

This work explores conditions under which multi-finger grasping algorithms can attain robust sim-to-real transfer. While numerous large datasets facilitate learning generative models for multi-finger grasping at scale, reliable real-world dexterous grasping remains challenging, with most methods degrading when deployed on hardware. An alternate strategy is to use discriminative grasp evaluation models for grasp selection and refinement, conditioned on real-world sensor measurements. This paradigm has produced state-of-the-art results for vision-based parallel-jaw grasping, but remains unproven in the multi-finger setting. In this work, we find that existing datasets and methods have been insufficient for training discriminitive models for multi-finger grasping. To train grasp evaluators at scale, datasets must provide on the order of millions of grasps, including both positive and negative examples, with corresponding visual data resembling measurements at inference time. To that end, we release a new, open-source dataset of 3.5M grasps on 4.3K objects annotated with RGB images, point clouds, and trained NeRFs. Leveraging this dataset, we train vision-based grasp evaluators that outperform both analytic and generative modeling-based baselines on extensive simulated and real-world trials across a diverse range of objects. We show via numerous ablations that the key factor for performance is indeed the evaluator, and that its quality degrades as the dataset shrinks, demonstrating the importance of our new dataset. Project website at: https://sites.google.com/view/get-a-grip-dataset.

The robotics research field lacks formalized definitions and frameworks for evaluating advanced capabilities including generalizability (the ability for robots to perform tasks under varied contexts) and reproducibility (the performance of a reproduced robot capability in different labs under the same experimental conditions). This paper presents an initial conceptual framework, MIRRER, that unites the concepts of performance evaluation, benchmarking, and reproduced/replicated experimentation in order to facilitate comparable robotics research. Several open issues with the application of the framework are also presented.

Grasping objects with limited or no prior knowledge about them is a highly relevant skill in assistive robotics. Still, in this general setting, it has remained an open problem, especially when it comes to only partial observability and versatile grasping with multi-fingered hands. We present a novel, fast, and high fidelity deep learning pipeline consisting of a shape completion module that is based on a single depth image, and followed by a grasp predictor that is based on the predicted object shape. The shape completion network is based on VQDIF and predicts spatial occupancy values at arbitrary query points. As grasp predictor, we use our two-stage architecture that first generates hand poses using an autoregressive model and then regresses finger joint configurations per pose. Critical factors turn out to be sufficient data realism and augmentation, as well as special attention to difficult cases during training. Experiments on a physical robot platform demonstrate successful grasping of a wide range of household objects based on a depth image from a single viewpoint. The whole pipeline is fast, taking only about 1 s for completing the object's shape (0.7 s) and generating 1000 grasps (0.3 s).

Multiple-suction-cup grasping can improve the efficiency of bin picking in cluttered scenes. In this paper, we propose a grasp planner for a vacuum gripper to use multiple suction cups to simultaneously grasp multiple objects or an object with a large surface. To take on the challenge of determining where to grasp and which cups to activate when grasping, we used 3D convolution to convolve the affordable areas inferred by neural network with the gripper kernel in order to find graspable positions of sampled gripper orientations. The kernel used for 3D convolution in this work was encoded including cup ID information, which helps to directly determine which cups to activate by decoding the convolution results. Furthermore, a sorting algorithm is proposed to find the optimal grasp among the candidates. Our planner exhibited good generality and successfully found multiple-cup grasps in previous affordance map datasets. Our planner also exhibited improved picking efficiency using multiple suction cups in physical robot picking experiments. Compared with single-object (single-cup) grasping, multiple-cup grasping contributed to 1.45x, 1.65x, and 1.16x increases in efficiency for picking boxes, fruits, and daily necessities, respectively.

We introduce OPEND, a benchmark for learning how to use a hand to open cabinet doors or drawers in a photo-realistic and physics-reliable simulation environment driven by language instruction. To solve the task, we propose a multi-step planner composed of a deep neural network and rule-base controllers. The network is utilized to capture spatial relationships from images and understand semantic meaning from language instructions. Controllers efficiently execute the plan based on the spatial and semantic understanding. We evaluate our system by measuring its zero-shot performance in test data set. Experimental results demonstrate the effectiveness of decision planning by our multi-step planner for different hands, while suggesting that there is significant room for developing better models to address the challenge brought by language understanding, spatial reasoning, and long-term manipulation. We will release OPEND and host challenges to promote future research in this area.

We consider a novel problem where multiple rigid convex polygonal objects rest in randomly placed positions and orientations on a planar surface visible from an overhead camera. The objective is to efficiently grasp and transport all objects into a bin using multi-object push-grasps, where multiple objects are pushed together to facilitate multi-object grasping. We provide necessary conditions for frictionless multi-object push-grasps and apply these to filter inadmissible grasps in a novel multi-object grasp planner. We find that our planner is 19 times faster than a Mujoco simulator baseline. We also propose a picking algorithm that uses both single- and multi-object grasps to pick objects. In physical grasping experiments comparing performance with a single-object picking baseline, we find that the frictionless multi-object grasping system achieves 13.6\% higher grasp success and is 59.9\% faster, from 212 PPH to 340 PPH. See \url{https://sites.google.com/view/multi-object-grasping} for videos and code.