diff --git a/_data/pubs/2025.yml b/_data/pubs/2025.yml index 0afa273..81c828e 100644 --- a/_data/pubs/2025.yml +++ b/_data/pubs/2025.yml @@ -1,3 +1,11 @@ +- title: "Imitation Learning-based Control of Brachiation Motion with Anthropomorphic Hands" + authors: Anubhav Tripathi, Nagamanikandan Govindan, Harikumar Kandath + venue: 2025 25th International Conference on Control, Automation and Systems (ICCAS) + link: # https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=11301396 + url: /publications/2025/Anubhav_Imitation + display: Project Page + id: hkandath + featured: 1 - title: "Three Dimensional Waypoint Navigation for Fixed-wing Micro Aerial Vehicles using Integrated Guidance and Control Framework" authors: Harikumar Kandath, Jinraj V Pushpangathan, M Seetharama Bhat diff --git a/_pages/project-pages/2025/Anubhav_Imitation.md b/_pages/project-pages/2025/Anubhav_Imitation.md new file mode 100644 index 0000000..c5afc16 --- /dev/null +++ b/_pages/project-pages/2025/Anubhav_Imitation.md @@ -0,0 +1,28 @@ +--- +layout: project-page-new +title: "Imitation Learning-based Control of Brachiation Motion with Anthropomorphic Hands" +authors: + - name: Anubhav Tripathi + sup: 1 + - name: Nagamanikandan Govindan + sup: 2 + - name: Harikumar Kandath + sup: 1 +affiliations: + - name: Robotics Research Center, IIIT Hyderabad, India + link: https://robotics.iiit.ac.in + sup: 1 + - name: Department of Mechanical Engineering, IIITDM Kancheepuram + link: https://www.iiitdm.ac.in/academics/departments/mech + sup: 2 +permalink: /publications/2025/Anubhav_Tripathi/ +abstract: "Brachiation, inspired by ape locomotion, involves swinging from one substrate to another. Existing approaches typically rely on simple grippers and computationally expensive optimal control to compute feasible states and control trajectories. In contrast, learning-based methods often lack physical modeling and require extensive training data. We present a brachiating system using high degree-of-freedom anthropomorphic hands to generate swing trajectories and perform stable grasps in a physics-based simulation environment (MuJoCo). An optimal open-loop trajectory is first generated via trajectory optimization based on a desired grasp location. A tracking controller follows this reference, while a grasping controller activates upon proximity to ensure secure contact. To reduce computational cost, we train a Generative Adversarial Imitation Learning (GAIL) policy using expert trajectories from the optimization framework. The GAIL-based controller generalizes to perturbed conditions and eliminates the need for repeated re-optimization, significantly lowering computation time. It also adapts to varying initial configurations, removing the requirement to rerun optimization for each case. We compare the learned model with a traditional optimal controller and demonstrate marked improvements in both computational efficiency and versatility." +#project_page: https://imagine-2-drive.github.io/ +paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=11301396 +#code: https://github.com/Smart-Wheelchair-RRC/CrowdSurfer +#supplement: https://arxiv.org/abs/2409.16011 +#video: https://iiithydresearch-my.sharepoint.com/personal/shreya_bollimuntha_research_iiit_ac_in/_layouts/15/stream.aspx?id=%2Fpersonal%2Fshreya%5Fbollimuntha%5Fresearch%5Fiiit%5Fac%5Fin%2FDocuments%2FAttachments%2FICRA%5F2025%2Emp4&ga=1&referrer=StreamWebApp%2EWeb&referrerScenario=AddressBarCopied%2Eview%2Edc06e0cd%2Dbfc3%2D4581%2D9eef%2Da7753f1e437a +#iframe: https://www.youtube.com/embed/BMDCYdxfaXM +#demo: https://anyloc.github.io/#interactive_demo + +--- \ No newline at end of file diff --git a/_pages/project-pages/2025/Harikumar_Three.md b/_pages/project-pages/2025/Harikumar_Three.md index e69de29..5e9ddbd 100644 --- a/_pages/project-pages/2025/Harikumar_Three.md +++ b/_pages/project-pages/2025/Harikumar_Three.md @@ -0,0 +1,32 @@ +--- +layout: project-page-new +title: "Three Dimensional Waypoint Navigation for Fixed-wing Micro Aerial Vehicles using Integrated Guidance and Control Framework" +authors: + - name: Harikumar Kandath + sup: 1 + - name: Jinraj V Pushpangathan + sup: 2 + - name: M Seetharama Bhat + sup: 3 +affiliations: + - name: Robotics Research Center, IIIT Hyderabad, India + link: https://robotics.iiit.ac.in + sup: 1 + - name: Department of Aerospace Engineering Amrita School of Engineering, Coimbatore + link: https://www.amrita.edu/school/engineering/coimbatore/aerospace/ + sup: 2 + - name: Department of Aerospace Engineering IISc Bengaluru, India + link: https://aero.iisc.ac.in/ + sup: 3 +permalink: /publications/2025/Harikumar_Three/ +abstract: "This paper presents an integrated guidance and control (IGC) framework for the three dimensional (3D) waypoint navigation of a fixed-wing micro aerial vehicle (MAV). The proposed IGC framework incorporates the miss distance into the state space model, and yields a single stage solution for 3D waypoint following. A H∞ static output feedback controller is designed for the linearized IGC state space model, stabilizing the open loop unstable spiral mode. The closed-loop Integrated +Guidance and Control (IGC) framework’s performance and stability are validated by high-fidelity nonlinear simulations for three-dimensional waypoint tracking." +#project_page: https://dualarmvil.github.io/Dual-Arm-VIL/ +paper: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=11213103 +#code: https://github.com/Smart-Wheelchair-RRC/CrowdSurfer +#supplement: https://arxiv.org/abs/2409.16011 +#video: https://iiithydresearch-my.sharepoint.com/personal/shreya_bollimuntha_research_iiit_ac_in/_layouts/15/stream.aspx?id=%2Fpersonal%2Fshreya%5Fbollimuntha%5Fresearch%5Fiiit%5Fac%5Fin%2FDocuments%2FAttachments%2FICRA%5F2025%2Emp4&ga=1&referrer=StreamWebApp%2EWeb&referrerScenario=AddressBarCopied%2Eview%2Edc06e0cd%2Dbfc3%2D4581%2D9eef%2Da7753f1e437a +#iframe: https://www.youtube.com/embed/BMDCYdxfaXM +#demo: https://anyloc.github.io/#interactive_demo + +--- \ No newline at end of file