Robot trajectories used for learning end-to-end robot policies typically contain end-effector and gripper position, workspace images, and language. Policies learned from such trajectories are unsuitable for delicate grasping, which require tightly coupled and precise gripper force and gripper position. We collect and make publically available 130 trajectories with force feedback of successful grasps on 30 unique objects. Our current-based method for sensing force, albeit noisy, is gripper-agnostic and requires no additional hardware. We train and evaluate two diffusion policies: one with (forceful) the collected force feedback and one without (position-only). We find that forceful policies are superior to position-only policies for delicate grasping and are able to generalize to unseen delicate objects, while reducing grasp policy latency by near 4x, relative to LLM-based methods. With our promising results on limited data, we hope to signal to others to consider investing in collecting force and other such tactile information in new datasets, enabling more robust, contact-rich manipulation in future robot foundation models.

Reference

W. Xie, S. Caldararu, N. Correll. Just Add Force for Delicate Robot Policies. , 2024. 

Off

Large language models (LLMs) can provide rich physical descriptions of most worldly objects, allowing robots to achieve more informed and capable grasping. We leverage LLMs’ common sense physical reasoning and code-writing abilities to infer an object’s physical characteristics—mass, friction coefficient, and spring constant —from a semantic description, and then translate those characteristics into an executable adaptive grasp policy. Using a current-controllable, two-finger gripper with a built-in depth camera, we demonstrate that LLM-generated, physically-grounded grasp policies outperform traditional grasp policies on a custom benchmark of 12 delicate and deformable items including food, produce, toys, and other everyday items, spanning two orders of magnitude in mass and required pick-up force. We also demonstrate how compliance feedback from DeliGrasp policies can aid in downstream tasks such as measuring produce ripeness. Our code and videos are available at: .

References

Xie, W., Valentini, M., Lavering, J. and Correll, N., 2024. DeliGrasp: Inferring Object Properties with LLMs for Adaptive Grasp Policies. In 8th Annual Conference on Robot Learning.

Xie, W., Lavering, J. and Correll, N., 2024. DeliGrasp: Inferring Object Mass, Friction, and Compliance with LLMs for Adaptive and Minimally Deforming Grasp Policies. .

Off

Shape displays that actively manipulate surface geometry are an expanding robotics domain with applications to haptics, manufacturing, aerodynamics, and more. However, existing displays often lack high-fidelity shape morphing, high-speed deformation, and embedded state sensing, limiting their potential uses. Here, we demonstrate a multifunctional soft-shape display driven by a 10 × 10 array of scalable cellular units which combine high-speed electrohydraulic soft actuation, magnetic-based sensing, and control circuitry. We report high-performance reversible shape morphing up to 50 Hz, sensing of surface deformations with 0.1 mm sensitivity, and external forces with 50 mN sensitivity in each cell, which we demonstrate across a multitude of applications including user interaction, image display, sensing of object mass, and dynamic manipulation of solids and liquids. This work showcases the rich multifunctionality and high-performance capabilities that arise from tightly-integrating large numbers of electrohydraulic actuators, soft sensors, and controllers at a previously undemonstrated scale in soft robotics.

References

B. K. Johnson, M. Naris, V. Sundaram, A. Volchko, K. Ly, S. K. Mitchell, E. Acome, N. Kellaris, C. Keplinger, N. Correll, J. S. Humbert & M. E. Rentschler. . Nature Communications volume 14, Article number: 4516 (2023)

Off

We describe a force-controlled robotic gripper with built-in tactile and 3D perception. We also describe a complete autonomous manipulation pipeline consisting of object detection, segmentation, point cloud processing, force-controlled manipulation, and symbolic (re)-planning. The design emphasizes versatility in terms of applications, manufacturability, use of commercial off-the-shelf parts, and open-source software. We validate the design by characterizing force control (achieving up to 32N, controllable in steps of 0.08N), force measurement, and two manipulation demonstrations: assembly of the Siemens gear assembly problem, and a sensor-based stacking task requiring replanning. These demonstrate robust execution of long sequences of sensor-based manipulation tasks, which makes the resulting platform a solid foundation for researchers in task-and-motion planning, educators, and quick prototyping of household and warehouse automation tasks.  

References

N. Correll, D. Kriegman, S. Otte and J. Watson. A versatile robotic hand with 3D perception, force sensing for autonomous manipulation. In Proceedings of Workshop on , Robotics: Science and Systems, Daegu, Korea.

Off

Peg-in-hole assembly of tightly fitting parts often requires multiple attempts. Parts need to be put together by performing a wiggling motion of undetermined length and can get stuck, requiring a restart. Recognizing unsuccessful insertion attempts early can help in reducing the makespan of the assembly. This can be achieved by analyzing time-series data from force and torque measurements. We describe a transformer neural network model that is three times faster, i.e. requiring much shorter time series, for predicting failure than a dilated fully convolutional neural network. Albeit the transformer provides predictions with higher confidence, it does so at reduced accuracy. Yet, being able to call unsuccessful attempts early, makespan can be reduced by almost 40% which we show using a dataset with force-torque data from 241 peg-in-hole assembly runs with known outcomes. 

References

R. Montané-Güell, J. Watson and N. Correll, 2023. Early failure prediction during robotic assembly using Transformers. In Proceedings of Workshop on  at Robotics: Science and Systems, Daegu, Korea. 

Off

Sensory feedback provided by prosthetic hands shows promise in increasing functional abilities and promoting embodiment of the prosthetic device. However, sensory feedback is limited based on where sensors are placed on the prosthetic device and has mainly focused on sensorizing the fingertips. Here we describe distributed tactile sensors for the palmar surfaces of prosthetic hands. We believe a sensing system that can detect interactions across the palmar surfaces in addition to the fingertips will further improve the experience for the prosthetic user and may increase embodiment of the device as well. This work details the design of a compliant distributed sensor which consists of PiezoResistive and PiezoElectric layers to produce a robust force measurement of both static and dynamic loads. This assembled sensor system is easy to customize to cover different areas of the prosthetic hand, simple to scale up, and flexible to different fabrication form-factors. The experimental results detail a load estimation accuracy of 95.4% and sensor response time of less than 200ms. Cycle tests of each sensor shows a drifting of within 10% of sensing capability under load and 6.37% in a no-load longitudinal test. These validation experiments reinforce the ability of the DualPiezo structure to provide a valuable sensor design for the palmar surfaces of prosthetic hands.

References

Truong, H., Correll, N. and Segil, J., 2023, April. Distributed Tactile Sensors for Palmar Surfaces of Prosthetic Hands. In 2023 11th International IEEE/EMBS Conference on Neural Engineering (NER) (pp. 1-4). IEEE. []

Off

Uncertainty in perception, actuation, and the environment often require multiple attempts for a robotic task to be successful. We study a class of problems providing (1) low-entropy indicators of terminal success / failure, and (2) unreliable (high-entropy) data to predict the final outcome of an ongoing task. Examples include a robot trying to connect with a charging station, parallel parking, or assembling a tightly-fitting part. The ability to restart after predicting failure early, versus simply running to failure, can significantly decrease the makespan, that is, the total time to completion, with the drawback of potentially short-cutting an otherwise successful operation. Assuming task running times to be Poisson distributed, and using a Markov Jump process to capture the dynamics of the underlying Markov Decision Process, we derive a closed form solution that predicts makespan based on the confusion matrix of the failure predictor. This allows the robot to learn failure prediction in a production environment, and only adopt a preemptive policy when it actually saves time. We demonstrate this approach using a robotic peg-in-hole assembly problem using a real robotic system. Failures are predicted by a dilated convolutional network based on force-torque data, showing an average makespan reduction from 101s to 81s (N=120, p<0.05). We posit that the proposed algorithm generalizes to any robotic behavior with an unambiguous terminal reward, with wide ranging applications on how robots can learn and improve their behaviors in the wild.

References

Watson, J. and Correll, N., 2023. . Int. Conf. on Intelligent Robots and Systems (IROS), Detroit, MI.

Off

The need to create more viable soft sensors is increasing in tandem with the growing interest in soft robots. Several sensing methods, like capacitive stretch sensing and intrinsic capacitive self-sensing, have proven to be useful when controlling soft electro-hydraulic actuators, but are still problematic. This is due to challenges around high-voltage electronic interference or the inability to accurately sense the actuator at higher actuation frequencies. These issues are compounded when trying to sense and control the movement of a multiactuator system. To address these shortcomings, we describe a two-part magnetic sensing mechanism to measure the changes in displacement of an electro-hydraulic (HASEL) actuator. Our magnetic sensing mechanism can achieve high accuracy and precision for the HASEL actuator displacement range, and accurately tracks motion at actuation frequencies up to 30 Hz, while being robust to changes in ambient temperature and relative humidity. The high accuracy of the magnetic sensing mechanism is also further emphasized in the gripper demonstration. Using this sensing mechanism, we can detect submillimeter difference in the diameters of three tomatoes. Finally, we successfully perform closed-loop control of one folded HASEL actuator using the sensor, which is then scaled into a deformable tilting platform of six units (one HASEL actuator and one sensor) that control a desired end effector position in 3D space. This work demonstrates the first instance of sensing electro-hydraulic deformation using a magnetic sensing mechanism. The ability to more accurately and precisely sense and control HASEL actuators and similar soft actuators is necessary to improve the abilities of soft, robotic platforms.

Reference

Sundaram, V., Ly, K., Johnson, B.K., Naris, M., Anderson, M.P., Humbert, J.S., Correll, N. and Rentschler, M., 2022. Embedded Magnetic Sensing for Feedback Control of Soft HASEL Actuators. IEEE Transactions on Robotics. []

Off

Textbooks that provide a broad algorithmic perspective on the mechanics and dynamics of robots almost unfailingly serve students at the graduate level. Introduction to Autonomous Robots offers a much-needed resource for teaching third- and fourth-year undergraduates the computational fundamentals behind the design and control of autonomous robots. The authors use a class-tested and accessible approach to present progressive, step-by-step development concepts, alongside a wide range of real-world examples and fundamental concepts in mechanisms, sensing and actuation, computation, and uncertainty. Throughout, the authors balance the impact of hardware (mechanism, sensor, actuator) and software (algorithms) in teaching robot autonomy.

Rigorous and tested in the classroom, Introduction to Autonomous Robots is written for engineering and computer science undergraduates with a sophomore-level understanding of linear algebra, probability theory, trigonometry, and statistics. The text covers topics like basic concepts in robotic mechanisms like locomotion and grasping, plus the resulting forces; operation principles of sensors and actuators; basic algorithms for vision and feature detection; an introduction to artificial neural networks, including convolutional and recurrent variants. The authors have included QR codes in the text guide readers to online lecture videos and animations. The book also features extensive appendices focus on project-based curricula, pertinent areas of mathematics, backpropagation, writing a research paper, and other topics, and is accompanied by a growing library of exercises in an open-source, platform-independent simulation (Webots).

Website

Reference

Correll, Nikolaus, Bradley Hayes, Christoffer Heckman, and Alessandro Roncone. Introduction to Autonomous Robots: Mechanisms, Sensors, Actuators, and Algorithms. MIT Press, 2022. [] 

Off

We present a novel augmented reality (AR) framework to show relevant information about swarm dynamics to a user in the absence of markers by using blinking frequency to distinguish between groups in the swarm. In order to distinguish between groups, clusters of the same group are identified by blinking at a specific time interval that is distinct from the time interval at which their neighbors blink. The problem is thus to find blinking sequences that are distinct for each group with respect to the group’s neighbors. Selecting an appropriate sequence is an instance of the distributed graph coloring problem, which can be solved in O(log(n)) time with n being the number of robots involved. We demonstrate our approach using a swarm chemistry simulation in which robots simulate individual atoms that form molecules following the rules of chemistry. An AR display is then used to display information about the internal state of individual swarm members as well as their topological relationship, corresponding to molecular bonds in a context that uses robot swarms to teach basic chemistry concepts.

Reference

Batra, Sumeet, John Klingner, and Nikolaus Correll. "Augmented reality for human–swarm interaction in a swarm-robotic chemistry simulation." Artificial Life and Robotics (2022): 1-9. []

Off