Search

We introduce a novel approach that combines tactile estimation and control for in-hand object manipulation. By integrating measurements from robot kinematics and an image-based tactile sensor, our framework estimates and tracks object pose while simultaneously generating motion plans in a receding horizon fashion to control the pose of a grasped object. This approach consists of a discrete pose estimator that tracks the most likely sequence of object poses in a coarsely discretized grid, and a continuous pose estimator-controller to refine the pose estimate and accurately manipulate the pose of the grasped object. Our method is tested on diverse objects and configurations, achieving desired manipulation objectives and outperforming single-shot methods in estimation accuracy. The proposed approach holds potential for tasks requiring precise manipulation and limited intrinsic in-hand dexterity under visual occlusion, laying the foundation for closed-loop behavior in applications such as regrasping, insertion, and tool use. Please see https://sites.google.com/view/texterity for videos of real-world demonstrations., Comment: project website: https://sites.google.com/view/texterity. arXiv admin note: substantial text overlap with arXiv:2401.10230

We introduce a novel approach that combines tactile estimation and control for in-hand object manipulation. By integrating measurements from robot kinematics and an image-based tactile sensor, our framework estimates and tracks object pose while simultaneously generating motion plans to control the pose of a grasped object. This approach consists of a discrete pose estimator that uses the Viterbi decoding algorithm to find the most likely sequence of object poses in a coarsely discretized grid, and a continuous pose estimator-controller to refine the pose estimate and accurately manipulate the pose of the grasped object. Our method is tested on diverse objects and configurations, achieving desired manipulation objectives and outperforming single-shot methods in estimation accuracy. The proposed approach holds potential for tasks requiring precise manipulation in scenarios where visual perception is limited, laying the foundation for closed-loop behavior applications such as assembly and tool use. Please see supplementary videos for real-world demonstration at https://sites.google.com/view/texterity., Comment: 8 pages, 5 figures, submitted to ICRA 2024

We propose a framework for optimizing a planar parallel-jaw gripper for use with multiple objects. While optimizing general-purpose grippers and contact locations for grasps are both well studied, co-optimizing grasps and the gripper geometry to execute them receives less attention. As such, our framework synthesizes grippers optimized to stably grasp sets of polygonal objects. Given a fixed number of contacts and their assignments to object faces and gripper jaws, our framework optimizes contact locations along these faces, gripper pose for each grasp, and gripper shape. Our key insights are to pose shape and contact constraints in frames fixed to the gripper jaws, and to leverage the linearity of constraints in our grasp stability and gripper shape models via an augmented Lagrangian formulation. Together, these enable a tractable nonlinear program implementation. We apply our method to several examples. The first illustrative problem shows the discovery of a geometrically simple solution where possible. In another, space is constrained, forcing multiple objects to be contacted by the same features as each other. Finally a toolset-grasping example shows that our framework applies to complex, real-world objects. We provide a physical experiment of the toolset grasps., Comment: 2023 IEEE IROS conference

In this work, we build on our method for manipulating unknown objects via contact configuration regulation: the estimation and control of the location, geometry, and mode of all contacts between the robot, object, and environment. We further develop our estimator and controller to enable manipulation through more complex contact interactions, including intermittent contact between the robot/object, and multiple contacts between the object/environment. In addition, we support a larger set of contact geometries at each interface. This is accomplished through a factor graph based estimation framework that reasons about the complementary kinematic and wrench constraints of contact to predict the current contact configuration. We are aided by the incorporation of a limited amount of visual feedback; which when combined with the available F/T sensing and robot proprioception, allows us to differentiate contact modes that were previously indistinguishable. We implement this revamped framework on our manipulation platform, and demonstrate that it allows the robot to perform a wider set of manipulation tasks. This includes, using a wall as a support to re-orient an object, or regulating the contact geometry between the object and the ground. Finally, we conduct ablation studies to understand the contributions from visual and tactile feedback in our manipulation framework. Our code can be found at: https://github.com/mcubelab/pbal.

Large Language Models (LLMs) have the potential to revolutionize automated traceability by overcoming the challenges faced by previous methods and introducing new possibilities. However, the optimal utilization of LLMs for automated traceability remains unclear. This paper explores the process of prompt engineering to extract link predictions from an LLM. We provide detailed insights into our approach for constructing effective prompts, offering our lessons learned. Additionally, we propose multiple strategies for leveraging LLMs to generate traceability links, improving upon previous zero-shot methods on the ranking of candidate links after prompt refinement. The primary objective of this paper is to inspire and assist future researchers and engineers by highlighting the process of constructing traceability prompts to effectively harness LLMs for advancing automatic traceability.

Existing robotic systems have a clear tension between generality and precision. Deployed solutions for robotic manipulation tend to fall into the paradigm of one robot solving a single task, lacking precise generalization, i.e., the ability to solve many tasks without compromising on precision. This paper explores solutions for precise and general pick-and-place. In precise pick-and-place, i.e. kitting, the robot transforms an unstructured arrangement of objects into an organized arrangement, which can facilitate further manipulation. We propose simPLE (simulation to Pick Localize and PLacE) as a solution to precise pick-and-place. simPLE learns to pick, regrasp and place objects precisely, given only the object CAD model and no prior experience. We develop three main components: task-aware grasping, visuotactile perception, and regrasp planning. Task-aware grasping computes affordances of grasps that are stable, observable, and favorable to placing. The visuotactile perception model relies on matching real observations against a set of simulated ones through supervised learning. Finally, we compute the desired robot motion by solving a shortest path problem on a graph of hand-to-hand regrasps. On a dual-arm robot equipped with visuotactile sensing, we demonstrate pick-and-place of 15 diverse objects with simPLE. The objects span a wide range of shapes and simPLE achieves successful placements into structured arrangements with 1mm clearance over 90% of the time for 6 objects, and over 80% of the time for 11 objects. Videos are available at http://mcube.mit.edu/research/simPLE.html ., Comment: 33 pages, 6 figures, 2 tables, submitted to Science Robotics

We propose a system for rearranging objects in a scene to achieve a desired object-scene placing relationship, such as a book inserted in an open slot of a bookshelf. The pipeline generalizes to novel geometries, poses, and layouts of both scenes and objects, and is trained from demonstrations to operate directly on 3D point clouds. Our system overcomes challenges associated with the existence of many geometrically-similar rearrangement solutions for a given scene. By leveraging an iterative pose de-noising training procedure, we can fit multi-modal demonstration data and produce multi-modal outputs while remaining precise and accurate. We also show the advantages of conditioning on relevant local geometric features while ignoring irrelevant global structure that harms both generalization and precision. We demonstrate our approach on three distinct rearrangement tasks that require handling multi-modality and generalization over object shape and pose in both simulation and the real world. Project website, code, and videos: https://anthonysimeonov.github.io/rpdiff-multi-modal/, Comment: Project page: https://anthonysimeonov.github.io/rpdiff-multi-modal/

Software traceability is the process of establishing and maintaining relationships between artifacts in a software system. This process is crucial to many engineering processes, particularly for safety critical projects; however, it is labor-intensive and error-prone. Automated traceability has been a long awaited tool for project managers of these systems, and due to the semantic similarities between linked artifacts, NLP techniques, such as transformer models, may be leveraged to accomplish this task. SAFA.ai is a startup focusing on fine-tuning project-specific models that deliver automated traceability in a near real-time environment. The following paper describes the challenges that characterize commercializing software traceability and highlights possible future directions.

The following paper investigates the effectiveness of incorporating human salience into the task of calorie prediction from images of food. We observe a 32.2% relative improvement when incorporating saliency maps on the images of food highlighting the most calorie regions. We also attempt to further improve the accuracy by starting the best models using pre-trained weights on similar tasks of mass estimation and food classification. However, we observe no improvement. Surprisingly, we also find that our best model was not able to surpass the original performance published alongside the test dataset, Nutrition5k. We use ResNet50 and Xception as the base models for our experiment.

We propose a method that simultaneously estimates and controls extrinsic contact with tactile feedback. The method enables challenging manipulation tasks that require controlling light forces and accurate motions in contact, such as balancing an unknown object on a thin rod standing upright. A factor graph-based framework fuses a sequence of tactile and kinematic measurements to estimate and control the interaction between gripper-object-environment, including the location and wrench at the extrinsic contact between the grasped object and the environment and the grasp wrench transferred from the gripper to the object. The same framework simultaneously plans the gripper motions that make it possible to estimate the state while satisfying regularizing control objectives to prevent slip, such as minimizing the grasp wrench and minimizing frictional force at the extrinsic contact. We show results with sub-millimeter contact localization error and good slip prevention even on slippery environments, for multiple contact formations (point, line, patch contact) and transitions between them. See supplementary video and results at https://sites.google.com/view/sim-tact., Comment: 2023 International Conference on Robotics and Automation (ICRA)

There is a persistent lack of funding, especially for SMEs, that cyclically worsens. The factoring and invoice discounting market appears to address delays in paying commercial invoices: sellers bring still-to-be-paid invoices to financial organizations, intermediaries, typically banks that provide an advance payment. This article contains research on novel decentralized approaches to said lending services without intermediaries by using liquidity pools and its associated heuristics, creating an Automated Market Maker. In our approach, the contributed collateral and the invoice trades with risk is measured with a formula: The Kelly criterion is used to calculate the optimal premium to be contributed to a liquidity pool in the funding of the said invoices. The behavior of the algorithm is studied in several scenarios of streams of invoices with representative amounts, collaterals, payment delays, and nonpayments rates or mora. We completed the study with hack scenarios with bogus, nonpayable invoices. As a result, we have created a resilient solution that performs the best with partially collateralized invoices. The outcome is decentralized market developed with the Kelly criterion that is reasonably resilient to a wide variety of the invoicing cases that provides sound profit to liquidity providers, and several premium distribution policies were checked that contributed with extra resilience to the performance of the algorithm., Comment: 43 pages, UCL-CBT Report

Cloth in the real world is often crumpled, self-occluded, or folded in on itself such that key regions, such as corners, are not directly graspable, making manipulation difficult. We propose a system that leverages visual and tactile perception to unfold the cloth via grasping and sliding on edges. By doing so, the robot is able to grasp two adjacent corners, enabling subsequent manipulation tasks like folding or hanging. As components of this system, we develop tactile perception networks that classify whether an edge is grasped and estimate the pose of the edge. We use the edge classification network to supervise a visuotactile edge grasp affordance network that can grasp edges with a 90% success rate. Once an edge is grasped, we demonstrate that the robot can slide along the cloth to the adjacent corner using tactile pose estimation/control in real time. See http://nehasunil.com/visuotactile/visuotactile.html for videos., Comment: Accepted at CoRL 2022. Project website: http://nehasunil.com/visuotactile/visuotactile.html

We present a method for performing tasks involving spatial relations between novel object instances initialized in arbitrary poses directly from point cloud observations. Our framework provides a scalable way for specifying new tasks using only 5-10 demonstrations. Object rearrangement is formalized as the question of finding actions that configure task-relevant parts of the object in a desired alignment. This formalism is implemented in three steps: assigning a consistent local coordinate frame to the task-relevant object parts, determining the location and orientation of this coordinate frame on unseen object instances, and executing an action that brings these frames into the desired alignment. We overcome the key technical challenge of determining task-relevant local coordinate frames from a few demonstrations by developing an optimization method based on Neural Descriptor Fields (NDFs) and a single annotated 3D keypoint. An energy-based learning scheme to model the joint configuration of the objects that satisfies a desired relational task further improves performance. The method is tested on three multi-object rearrangement tasks in simulation and on a real robot. Project website, videos, and code: https://anthonysimeonov.github.io/r-ndf/, Comment: CoRL 2022, first two authors contributed equally, website and code: https://anthonysimeonov.github.io/r-ndf/

We unveil the signature of many-body interference across dynamical regimes of the Bose-Hubbard model. Increasing the particles' indistinguishability enhances the temporal fluctuations of few-body observables, with a dramatic amplification at the onset of quantum chaos. By resolving the exchange symmetries of partially distinguishable particles, we explain this amplification as the fingerprint of the initial state's coherences in the eigenbasis., Comment: 5 pages, 2 figures + supplemental material

Multi-step forceful manipulation tasks, such as opening a push-and-twist childproof bottle, require a robot to make various planning choices that are substantially impacted by the requirement to exert force during the task. The robot must reason over discrete and continuous choices relating to the sequence of actions, such as whether to pick up an object, and the parameters of each of those actions, such how to grasp the object. To enable planning and executing forceful manipulation, we augment an existing task and motion planner with constraints that explicitly consider torque and frictional limits, captured through the proposed forceful kinematic chain constraint. In three domains, opening a childproof bottle, twisting a nut and cutting a vegetable, we demonstrate how the system selects from among a combinatorial set of strategies.We also show how cost-sensitive planning can be used to find strategies and parameters that are robust to uncertainty in the physical parameters., Comment: Accepted to IJRR (International Journal of Robotics Research). Supplemental Video: https://www.youtube.com/watch?v=r1L-gxufFuY

The dependence of the chaotic phase of the Bose-Hubbard Hamiltonian on particle number $N$, system size $L$ and particle density is investigated in terms of spectral and eigenstate features. We analyze the development of the chaotic phase as the limit of infinite Hilbert space dimension is approached along different directions, and show that the fastest route to chaos is the path at fixed density $n \lesssim 1$. The limit $N \to \infty$ at constant $L$ leads to a slower convergence of the chaotic phase towards the random matrix theory benchmarks. In this case, from the distribution of the eigenstate generalized fractal dimensions, the ergodic phase becomes more distinguishable from random matrix theory for larger $N$, in a similar way as along trajectories at fixed density., Comment: 9 pages, 8 figures

In this paper, we present Tac2Pose, an object-specific approach to tactile pose estimation from the first touch for known objects. Given the object geometry, we learn a tailored perception model in simulation that estimates a probability distribution over possible object poses given a tactile observation. To do so, we simulate the contact shapes that a dense set of object poses would produce on the sensor. Then, given a new contact shape obtained from the sensor, we match it against the pre-computed set using an object-specific embedding learned using contrastive learning. We obtain contact shapes from the sensor with an object-agnostic calibration step that maps RGB tactile observations to binary contact shapes. This mapping, which can be reused across object and sensor instances, is the only step trained with real sensor data. This results in a perception model that localizes objects from the first real tactile observation. Importantly, it produces pose distributions and can incorporate additional pose constraints coming from other perception systems, contacts, or priors. We provide quantitative results for 20 objects. Tac2Pose provides high accuracy pose estimations from distinctive tactile observations while regressing meaningful pose distributions to account for those contact shapes that could result from different object poses. We also test Tac2Pose on object models reconstructed from a 3D scanner, to evaluate the robustness to uncertainty in the object model. Finally, we demonstrate the advantages of Tac2Pose compared with three baseline methods for tactile pose estimation: directly regressing the object pose with a neural network, matching an observed contact to a set of possible contacts using a standard classification neural network, and direct pixel comparison of an observed contact with a set of possible contacts. Website: http://mcube.mit.edu/research/tac2pose.html, Comment: Submitted to IJRR, 22 pages + Appendix, 11 figures

Thin, reflective objects such as forks and whisks are common in our daily lives, but they are particularly challenging for robot perception because it is hard to reconstruct them using commodity RGB-D cameras or multi-view stereo techniques. While traditional pipelines struggle with objects like these, Neural Radiance Fields (NeRFs) have recently been shown to be remarkably effective for performing view synthesis on objects with thin structures or reflective materials. In this paper we explore the use of NeRF as a new source of supervision for robust robot vision systems. In particular, we demonstrate that a NeRF representation of a scene can be used to train dense object descriptors. We use an optimized NeRF to extract dense correspondences between multiple views of an object, and then use these correspondences as training data for learning a view-invariant representation of the object. NeRF's usage of a density field allows us to reformulate the correspondence problem with a novel distribution-of-depths formulation, as opposed to the conventional approach of using a depth map. Dense correspondence models supervised with our method significantly outperform off-the-shelf learned descriptors by 106% (PCK@3px metric, more than doubling performance) and outperform our baseline supervised with multi-view stereo by 29%. Furthermore, we demonstrate the learned dense descriptors enable robots to perform accurate 6-degree of freedom (6-DoF) pick and place of thin and reflective objects., Comment: ICRA 2022, Website: https://yenchenlin.me/nerf-supervision/

We present an approach to robotic manipulation of unknown objects through regulation of the object's contact configuration: the location, geometry, and mode of all contacts between the object, robot, and environment. A contact configuration constrains the forces and motions that can be applied to the object; however, synthesizing these constraints generally requires knowledge of the object's pose and geometry. We develop an object-agnostic approach for estimation and control that circumvents this need. Our framework directly estimates a set of wrench and motion constraints which it uses to regulate the contact configuration. We use this to reactively manipulate unknown planar objects in the gravity plane. A video describing our work can be found on our project page: http://mcube.mit.edu/research/contactConfig.html., Comment: Authors contributed equally, names listed in alphabetical order. ICRA 2022

We present Neural Descriptor Fields (NDFs), an object representation that encodes both points and relative poses between an object and a target (such as a robot gripper or a rack used for hanging) via category-level descriptors. We employ this representation for object manipulation, where given a task demonstration, we want to repeat the same task on a new object instance from the same category. We propose to achieve this objective by searching (via optimization) for the pose whose descriptor matches that observed in the demonstration. NDFs are conveniently trained in a self-supervised fashion via a 3D auto-encoding task that does not rely on expert-labeled keypoints. Further, NDFs are SE(3)-equivariant, guaranteeing performance that generalizes across all possible 3D object translations and rotations. We demonstrate learning of manipulation tasks from few (5-10) demonstrations both in simulation and on a real robot. Our performance generalizes across both object instances and 6-DoF object poses, and significantly outperforms a recent baseline that relies on 2D descriptors. Project website: https://yilundu.github.io/ndf/., Comment: Website: https://yilundu.github.io/ndf/. First two authors contributed equally (order determined by coin flip), last two authors equal advising

Specifying tasks with videos is a powerful technique towards acquiring novel and general robot skills. However, reasoning over mechanics and dexterous interactions can make it challenging to scale learning contact-rich manipulation. In this work, we focus on the problem of visual non-prehensile planar manipulation: given a video of an object in planar motion, find contact-aware robot actions that reproduce the same object motion. We propose a novel architecture, Differentiable Learning for Manipulation (\ours), that combines video decoding neural models with priors from contact mechanics by leveraging differentiable optimization and finite difference based simulation. Through extensive simulated experiments, we investigate the interplay between traditional model-based techniques and modern deep learning approaches. We find that our modular and fully differentiable architecture performs better than learning-only methods on unseen objects and motions. \url{https://github.com/baceituno/dlm}., Comment: Presented at CORL 2021

We propose a method that actively estimates contact location between a grasped rigid object and its environment and uses this as input to a peg-in-hole insertion policy. An estimation model and an active tactile feedback controller work collaboratively to estimate the external contacts accurately. The controller helps the estimation model get a better estimate by regulating a consistent contact mode. The better estimation makes it easier for the controller to regulate the contact. We then train an object-agnostic insertion policy that learns to use the series of contact estimates to guide the insertion of an unseen peg into a hole. In contrast with previous works that learn a policy directly from tactile signals, since this policy is in contact configuration space, it can be learned directly in simulation. Lastly, we demonstrate and evaluate the active extrinsic contact line estimation and the trained insertion policy together in a real experiment. We show that the proposed method inserts various-shaped test objects with higher success rates and fewer insertion attempts than previous work with end-to-end approaches. See supplementary video and results at https://sites.google.com/view/active-extrinsic-contact.

We investigate the chaotic phase of the Bose-Hubbard model [L. Pausch et al, Phys. Rev. Lett. 126, 150601 (2021)] in relation to the bosonic embedded random matrix ensemble, which mirrors the dominant few-body nature of many-particle interactions, and hence the Fock space sparsity of quantum many-body systems. The energy dependence of the chaotic regime is well described by the bosonic embedded ensemble, which also reproduces the Bose-Hubbard chaotic eigenvector features, quantified by the expectation value and eigenstate-to-eigenstate fluctuations of fractal dimensions. Despite this agreement, in terms of the fractal dimension distribution, these two models depart from each other and from the Gaussian orthogonal ensemble as Hilbert space grows. These results provide further evidence of a way to discriminate among different many-body Hamiltonians in the chaotic regime., Comment: 13 pages, 9 figures

A study of the dynamical formation of networks of friends and enemies in social media, in this case Twitter, is presented. We characterise the single node properties of such networks, as the clustering coefficient and the degree, to investigate the structure of links. The results indicate that the network is made from three kinds of nodes: one with high clustering coefficient but very small degree, a second group has zero clustering coefficient with variable degree, and finally, a third group in which the clustering coefficient as a function of the degree decays as a power law. This third group represents $\sim2\%$ of the nodes and is characteristic of dynamical networks with feedback. This part of the lattice seemingly represents strongly interacting friends in a real social network.

Object insertion is a classic contact-rich manipulation task. The task remains challenging, especially when considering general objects of unknown geometry, which significantly limits the ability to understand the contact configuration between the object and the environment. We study the problem of aligning the object and environment with a tactile-based feedback insertion policy. The insertion process is modeled as an episodic policy that iterates between insertion attempts followed by pose corrections. We explore different mechanisms to learn such a policy based on Reinforcement Learning. The key contribution of this paper is to demonstrate that it is possible to learn a tactile insertion policy that generalizes across different object geometries, and an ablation study of the key design choices for the learning agent: 1) the type of learning scheme: supervised vs. reinforcement learning; 2) the type of learning schedule: unguided vs. curriculum learning; 3) the type of sensing modality: force/torque (F/T) vs. tactile; and 4) the type of tactile representation: tactile RGB vs. tactile flow. We show that the optimal configuration of the learning agent (RL + curriculum + tactile flow) exposed to 4 training objects yields an insertion policy that inserts 4 novel objects with over 85.0% success rate and within 3~4 attempts. Comparisons between F/T and tactile sensing, shows that while an F/T-based policy learns more efficiently, a tactile-based policy provides better generalization.

This work presents a new version of the tactile-sensing finger GelSlim 3.0, which integrates the ability to sense high-resolution shape, force, and slip in a compact form factor for use with small parallel jaw grippers in cluttered bin-picking scenarios. The novel design incorporates the capability to use real-time analytic methods to measure shape, estimate the contact 3D force distribution, and detect incipient slip. To achieve a compact integration, we optimize the optical path from illumination source to camera and other geometric variables in a optical simulation environment. In particular, we optimize the illumination sources and a light shaping lens around the constraints imposed by the photometric stereo algorithm used for depth reconstruction. The optimized optical configuration is integrated into a finger design composed of robust and easily replaceable snap-to-fit fingetip module that allow for ease of manufacture, assembly, use, and repair. To stimulate future research in tactile-sensing and provide the robotics community access to reliable and easily-reproducible tactile finger with a diversity of sensing modalities, we open-source the design and software at https://github.com/mcubelab/gelslim.

This paper addresses the localization of contacts of an unknown grasped rigid object with its environment, i.e., extrinsic to the robot. We explore the key role that distributed tactile sensing plays in localizing contacts external to the robot, in contrast to the role that aggregated force/torque measurements play in localizing contacts on the robot. When in contact with the environment, an object will move in accordance with the kinematic and possibly frictional constraints imposed by that contact. Small motions of the object, which are observable with tactile sensors, indirectly encode those constraints and the geometry that defines them. We formulate the extrinsic contact sensing problem as a constraint-based estimation. The estimation is subject to the kinematic constraints imposed by the tactile measurements of object motion, as well as the kinematic (e.g., non-penetration) and possibly frictional (e.g., sticking) constraints imposed by rigid-body mechanics. We validate the approach in simulation and with real experiments on the case studies of fixed point and line contacts. This paper discusses the theoretical basis for the value of distributed tactile sensing in contrast to aggregated force/torque measurements. It also provides an estimation framework for localizing environmental contacts with potential impact in contact-rich manipulation scenarios such as assembling or packing., Comment: 6 pages, 8 figures, ICRA 2021

Multi-stage forceful manipulation tasks, such as twisting a nut on a bolt, require reasoning over interlocking constraints over discrete as well as continuous choices. The robot must choose a sequence of discrete actions, or strategy, such as whether to pick up an object, and the continuous parameters of each of those actions, such as how to grasp the object. In forceful manipulation tasks, the force requirements substantially impact the choices of both strategy and parameters. To enable planning and executing forceful manipulation, we augment an existing task and motion planner with controllers that exert wrenches and constraints that explicitly consider torque and frictional limits. In two domains, opening a childproof bottle and twisting a nut, we demonstrate how the system considers a combinatorial number of strategies and how choosing actions that are robust to parameter variations impacts the choice of strategy., Comment: Accepted to IEEE ICRA 2021. For videos see: https://mcube.mit.edu/forceful-manipulation/

We present the design, implementation, and evaluation of RF-Grasp, a robotic system that can grasp fully-occluded objects in unknown and unstructured environments. Unlike prior systems that are constrained by the line-of-sight perception of vision and infrared sensors, RF-Grasp employs RF (Radio Frequency) perception to identify and locate target objects through occlusions, and perform efficient exploration and complex manipulation tasks in non-line-of-sight settings. RF-Grasp relies on an eye-in-hand camera and batteryless RFID tags attached to objects of interest. It introduces two main innovations: (1) an RF-visual servoing controller that uses the RFID's location to selectively explore the environment and plan an efficient trajectory toward an occluded target, and (2) an RF-visual deep reinforcement learning network that can learn and execute efficient, complex policies for decluttering and grasping. We implemented and evaluated an end-to-end physical prototype of RF-Grasp. We demonstrate it improves success rate and efficiency by up to 40-50% over a state-of-the-art baseline. We also demonstrate RF-Grasp in novel tasks such mechanical search of fully-occluded objects behind obstacles, opening up new possibilities for robotic manipulation. Qualitative results (videos) available at rfgrasp.media.mit.edu

We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF). NeRFs have been shown to be remarkably effective for the task of view synthesis - synthesizing photorealistic novel views of real-world scenes or objects. In this work, we investigate whether we can apply analysis-by-synthesis via NeRF for mesh-free, RGB-only 6DoF pose estimation - given an image, find the translation and rotation of a camera relative to a 3D object or scene. Our method assumes that no object mesh models are available during either training or test time. Starting from an initial pose estimate, we use gradient descent to minimize the residual between pixels rendered from a NeRF and pixels in an observed image. In our experiments, we first study 1) how to sample rays during pose refinement for iNeRF to collect informative gradients and 2) how different batch sizes of rays affect iNeRF on a synthetic dataset. We then show that for complex real-world scenes from the LLFF dataset, iNeRF can improve NeRF by estimating the camera poses of novel images and using these images as additional training data for NeRF. Finally, we show iNeRF can perform category-level object pose estimation, including object instances not seen during training, with RGB images by inverting a NeRF model inferred from a single view., Comment: IROS 2021, Website: http://yenchenlin.me/inerf/

In this paper, we present an approach to tactile pose estimation from the first touch for known objects. First, we create an object-agnostic map from real tactile observations to contact shapes. Next, for a new object with known geometry, we learn a tailored perception model completely in simulation. To do so, we simulate the contact shapes that a dense set of object poses would produce on the sensor. Then, given a new contact shape obtained from the sensor output, we match it against the pre-computed set using the object-specific embedding learned purely in simulation using contrastive learning. This results in a perception model that can localize objects from a single tactile observation. It also allows reasoning over pose distributions and including additional pose constraints coming from other perception systems or multiple contacts. We provide quantitative results for four objects. Our approach provides high accuracy pose estimations from distinctive tactile observations while regressing pose distributions to account for those contact shapes that could result from different object poses. We further extend and test our approach in multi-contact scenarios where several tactile sensors are simultaneously in contact with the object. Website: http://mcube.mit.edu/research/tactile_loc_first_touch.html, Comment: CORL 2020, 5 figures + 2 in appendix Video: https://youtu.be/2ygtSJTmo08

We present a framework for solving long-horizon planning problems involving manipulation of rigid objects that operates directly from a point-cloud observation, i.e. without prior object models. Our method plans in the space of object subgoals and frees the planner from reasoning about robot-object interaction dynamics by relying on a set of generalizable manipulation primitives. We show that for rigid bodies, this abstraction can be realized using low-level manipulation skills that maintain sticking contact with the object and represent subgoals as 3D transformations. To enable generalization to unseen objects and improve planning performance, we propose a novel way of representing subgoals for rigid-body manipulation and a graph-attention based neural network architecture for processing point-cloud inputs. We experimentally validate these choices using simulated and real-world experiments on the YuMi robot. Results demonstrate that our method can successfully manipulate new objects into target configurations requiring long-term planning. Overall, our framework realizes the best of the worlds of task-and-motion planning (TAMP) and learning-based approaches. Project website: https://anthonysimeonov.github.io/rpo-planning-framework/., Comment: Conference on Robot Learning (CoRL 2020): Project website: https://anthonysimeonov.github.io/rpo-planning-framework/

Tactile perception is central to robot manipulation in unstructured environments. However, it requires contact, and a mature implementation must infer object models while also accounting for the motion induced by the interaction. In this work, we present a method to estimate both object shape and pose in real-time from a stream of tactile measurements. This is applied towards tactile exploration of an unknown object by planar pushing. We consider this as an online SLAM problem with a nonparametric shape representation. Our formulation of tactile inference alternates between Gaussian process implicit surface regression and pose estimation on a factor graph. Through a combination of local Gaussian processes and fixed-lag smoothing, we infer object shape and pose in real-time. We evaluate our system across different objects in both simulated and real-world planar pushing tasks., Comment: Camera-ready version to be presented at the 2021 IEEE International Conference on Robotics and Automation (ICRA 2021). For associated video file, see https://youtu.be/wdyagx5MM40