diff --git a/_data/pubs.yml b/_data/pubs.yml index 7f2eaa588bb6..93dd24b0066b 100644 --- a/_data/pubs.yml +++ b/_data/pubs.yml @@ -100,6 +100,28 @@ video_embed: tags: null +- title: "Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration" + authors: Xianyi Cheng, Sarvesh Patil, F. Zeynep Temel, Oliver Kroemer, Matthew T. Mason + venue: "IEEE Robotics and Automation Letters (RA-L), June 2024" + bib: > + @ARTICLE{cheng2024hidex, + author={Cheng, Xianyi and Patil, Sarvesh and Temel, Zeynep and Kroemer, Oliver and Mason, Matthew T.}, + journal={IEEE Robotics and Automation Letters}, + title={Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration}, + year={2024}, + volume={9}, + number={1}, + pages={390-397}, + doi={10.1109/LRA.2023.3333699}} + img: ../pics/HiDex.gif + abs: "Planning robot dexterity is challenging due to the non-smoothness introduced by contacts, intricate fine motions, and ever-changing scenarios. We present a hierarchical planning framework for dexterous robotic manipulation (HiDex). This framework explores in-hand and extrinsic dexterity by leveraging contacts. It generates rigid-body motions and complex contact sequences. Our framework is based on Monte-Carlo Tree Search and has three levels: 1) planning object motions and environment contact modes; 2) planning robot contacts; 3) path evaluation and control optimization. This framework offers two main advantages. First, it allows efficient global reasoning over high-dimensional complex space created by contacts. It solves a diverse set of manipulation tasks that require dexterity, both intrinsic (using the fingers) and extrinsic (also using the environment), mostly in seconds. Second, our framework allows the incorporation of expert knowledge and customizable setups in task mechanics and models. It requires minor modifications to accommodate different scenarios and robots. Hence, it provides a flexible and generalizable solution for various manipulation tasks. As examples, we analyze the results on 7 hand configurations and 15 scenarios. We demonstrate 8 tasks on two robot platforms." + links: + '[arXiv]': https://arxiv.org/abs/2307.00383 + short_id: HiDex + projects: delta_arrays + video_embed: + tags: null + - abs: "Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train “generalist” X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms." authors: Open X-Embodiment Collaboration, Jacky Liang, Kevin Zhang, Mohit Sharma, Oliver Kroemer, and 287 others award: Best Paper at ICRA 2024 @@ -183,6 +205,28 @@ venue: "Conference on Robot Learning (CoRL), Nov 2023" video_embed: null +- abs: "This paper presents a new type of distributed dexterous manipulator: delta arrays. Our delta array setup consists of 64 linearly-actuated delta robots with 3D-printed compliant linkages. Through the design of the individual delta robots, the modular array structure, and distributed communication and control, we study a wide range of in-plane and out-of-plane manipulations, as well as prehensile manipulations among subsets of neighboring delta robots. We also demonstrate dexterous manipulation capabilities of the delta array using reinforcement learning while leveraging the compliance to not break the end-effectors. Our evaluations show that the resulting 192 DoF compliant robot is capable of performing various coordinated distributed manipulations of a variety of objects, including translation, alignment, prehensile squeezing, lifting, and grasping." + authors: Sarvesh Patil, Tony Tao, Tess Hellebrekers, Oliver Kroemer, F. Zeynep Temel + bib: > + @inproceedings{Patil_2023, + title={Linear Delta Arrays for Compliant Dexterous Distributed Manipulation}, + url={http://dx.doi.org/10.1109/ICRA48891.2023.10160578}, + DOI={10.1109/icra48891.2023.10160578}, + booktitle={2023 IEEE International Conference on Robotics and Automation (ICRA)}, + publisher={IEEE}, + author={Patil, Sarvesh and Tao, Tony and Hellebrekers, Tess and Kroemer, Oliver and Temel, F. Zeynep}, + year={2023}, + month=may} + img: ../pics/delta_array.png + links: + '[arXiv]': https://arxiv.org/abs/2206.04596 + short_id: delta_arrays + title: "Linear Delta Arrays for Compliant Dexterous Distributed Manipulation" + venue: "International Conference on Robotics and Automation (ICRA), May 2023" + projects: delta_arrays + video_embed: + tags: null + - abs: "Operating under real world conditions is challenging due to the possibility of a wide range of failures induced by execution errors and state uncertainty. In relatively benign settings, such failures can be overcome by retrying or executing one of a small number of hand-engineered recovery strategies. By contrast, contact-rich sequential manipulation tasks, like opening doors and assembling furniture, are not amenable to exhaustive hand-engineering. To address this issue, we present a general approach for robustifying manipulation strategies in a sample-efficient manner. Our approach incrementally improves robustness by first discovering the failure modes of the current strategy via exploration in simulation and then learning additional recovery skills to handle these failures. To ensure efficient learning, we propose an online algorithm called Meta-Reasoning for Skill Learning (MetaReSkill) that monitors the progress of all recovery policies during training and allocates training resources to recoveries that are likely to improve the task performance the most. We use our approach to learn recovery skills for door-opening and evaluate them both in simulation and on a real robot with little fine-tuning. Compared to open-loop execution, our experiments show that even a limited amount of recovery learning improves task success substantially from 71% to 92.4% in simulation and from 75% to 90% on a real robot." authors: Shivam Vats, Maxim Likhachev, and Oliver Kroemer award: null @@ -241,6 +285,29 @@ venue: "Conference on Robot Learning (CoRL), Dec 2022" video_embed: null +- abs: "This paper presents the DeltaZ robot, a centimeter-scale, low-cost, delta-style robot that allows for a broad range of capabilities and robust functionalities. Current technologies allow DeltaZ to be 3D-printed from soft and rigid materials so that it is easy to assemble and maintain, and lowers the barriers to utilize. Functionality of the robot stems from its three translational degrees of freedom and a closed form kinematic solution which makes manipulation problems more intuitive compared to other manipulators. Moreover, the low cost of the robot presents an opportunity to democratize manipulators for a research setting. We also describe how the robot can be used as a reinforcement learning benchmark. Open-source 3D-printable designs and code are available to the public." + authors: Sarvesh Patil*, Samuel C. Alvares*, Pragna Mannam, Oliver Kroemer, F. Zeynep Temel + bib: > + @inproceedings{Patil_2022, + title={DeltaZ: An Accessible Compliant Delta Robot Manipulator for Research and Education}, + volume={22}, + url={http://dx.doi.org/10.1109/IROS47612.2022.9981257}, + DOI={10.1109/iros47612.2022.9981257}, + booktitle={2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, + publisher={IEEE}, + author={Patil, Sarvesh and Alvares, Samuel C. and Mannam, Pragna and Kroemer, Oliver and Temel, F. Zeynep}, + year={2022}, + month=oct, pages={13213–13219} } + img: ../pics/deltaz.jpeg + links: + '[arXiv]': https://arxiv.org/abs/2207.00721 + short_id: deltaZ + title: "DeltaZ: An Accessible Compliant Delta Robot Manipulator for Research and Education" + venue: "International Conference on Intelligent Robots and Systems (IROS), Oct 2022" + projects: delta_arrays + video_embed: + tags: null + - abs: "A key challenge in learning to perform manipu- lation tasks is selecting a suitable skill representation. While specific skill representations are often easier to learn, they are often only suitable for a narrow set of tasks. In most prior works, roboticists manually provide the robot with a suitable skill representation to use e.g. a neural network or DMPs. By contrast, we propose to allow the robot to select the most appropriate skill representation for the underlying task. Given the large space of skill representations, we utilize a single demonstration to select a small set of potential task-relevant representations. This set is then further refined using reinforcement learning to select the most suitable skill representation. Experiments in both simulation and real world show how our proposed approach leads to improved sample efficiency and enables directly learning on the real robot." authors: Mohit Sharma and Oliver Kroemer award: null diff --git a/_includes/render_pub.liquid b/_includes/render_pub.liquid new file mode 100644 index 000000000000..f3aef2ba44e2 --- /dev/null +++ b/_includes/render_pub.liquid @@ -0,0 +1,9 @@ + +**{{ pub.title }}.**
+{{ pub.authors }}.
*{{ pub.venue }}*{% + if pub.volume != None +%}, {{ pub.volume}}{% endif %}{% + if pub.number != None +%}({{ pub.number}}){% endif %} {{ pub.year }} {% + if pub.short_id != None +%}[pdf](/pdfs/{{ pub.short_id }}.pdf){% endif %} \ No newline at end of file diff --git a/pdfs/HiDex.pdf b/pdfs/HiDex.pdf new file mode 100644 index 000000000000..b4fed76b7828 Binary files /dev/null and b/pdfs/HiDex.pdf differ diff --git a/pdfs/deltaZ.pdf b/pdfs/deltaZ.pdf new file mode 100644 index 000000000000..333a7929eb7e Binary files /dev/null and b/pdfs/deltaZ.pdf differ diff --git a/pdfs/delta_arrays.pdf b/pdfs/delta_arrays.pdf new file mode 100644 index 000000000000..4b73531a0814 Binary files /dev/null and b/pdfs/delta_arrays.pdf differ diff --git a/pics/HiDex.gif b/pics/HiDex.gif new file mode 100644 index 000000000000..c4923464b0b0 Binary files /dev/null and b/pics/HiDex.gif differ diff --git a/pics/delta_array.png b/pics/delta_array.png new file mode 100644 index 000000000000..83be1196358a Binary files /dev/null and b/pics/delta_array.png differ diff --git a/pics/deltaz.jpeg b/pics/deltaz.jpeg new file mode 100644 index 000000000000..4383dc11f607 Binary files /dev/null and b/pics/deltaz.jpeg differ diff --git a/research.md b/research.md index 1aa256c47db2..0f7dbcc80d66 100755 --- a/research.md +++ b/research.md @@ -17,7 +17,7 @@ This project is focused on the development of robots that can safely and efficie

Relevant publications

-{% include render_pub_list.liquid variable="projects" value="delta_robots" check="contains" %} +{% include render_pub_list.liquid variable="projects" value="ballbot" check="contains" %}
@@ -34,14 +34,14 @@ The agriculture interaction project is focused on picking specialty crops such a

Relevant publications

-{% include render_pub_list.liquid variable="projects" value="delta_robots" check="contains" %} +{% include render_pub_list.liquid variable="projects" value="cornbot" check="contains" %}
## Delta Arrays -Delta Arrays +Delta Arrays The delta array project uses miniature delta bots on a robot's end-effector to enhance dexterity in manipulation tasks. We propose a novel manipulator: an 8x8 hexagonal grid of 64 linear soft delta robots, creating a 192 DoF-compliant system. This design explores complex multi-robot dexterous manipulation while maintaining accessibility. The 3D-printed soft TPU links provide mechanical compliance, allowing for safe collisions. Using reinforcement learning, we demonstrate various coordinated distributed manipulations, including translation, alignment, squeezing, lifting, and grasping of diverse objects. @@ -54,11 +54,30 @@ This project collaborates with Professor Zeynep Temel, aiming to develop new man

Relevant publications

-{% include render_pub_list.liquid variable="projects" value="delta_robots" check="contains" %} +{% include render_pub_list.liquid variable="projects" value="delta_arrays" check="contains" %}
+## Delta Hands + +Delta Hands + +DeltaHand is a synergistic robotic hand platform for dexterous manipulation. By leveraging the modularity of Delta robots, our hands are easy to configure to different degrees of freedom with actuation synergies. The manufacturing is low cost by using off-the-shelf materials (the robot can be manufactured in less than a day and costs under $800). We use soft Delta links for the fingers, and show that our hands can compliantly and safely interact with the environment. + +We demonstrate grasping of daily objects using our hand prototypes and teleoperating a 9-actuator Delta hand with a Franka robot arm for dexterous manipulation tasks, we show that we can easily control our hands by leveraging the synergy of our hands while maintaining the necessary dexterity. + +
+ +
+ +

Relevant publications

+ +
+{% include render_pub_list.liquid variable="projects" value="delta_robots" check="contains" %} +
+
+ # Past Projects ## Epson Manufacturing