diff --git a/_msc_projects_finished/24_JorisWeeda_SVGMPPI.html b/_msc_projects_finished/24_JorisWeeda_SVGMPPI.html new file mode 100644 index 0000000..02f6aba --- /dev/null +++ b/_msc_projects_finished/24_JorisWeeda_SVGMPPI.html @@ -0,0 +1,77 @@ +--- +title: "Pushing Through Clutter With Movability Awareness of Blocking Obstacles" +authors: + - name: "Joris Weeda" + url: "/" + - name: "Saray Bakker" + url: "https://scholar.google.com/citations?user=kAlAUFkAAAAJ&hl=nl" + - name: "Gang (Clarence) Chen" + url: "https://scholar.google.com/citations?hl=nl&user=fryWUUEAAAAJ" + - name: "Javier Alonso-Mora" + url: "https://scholar.google.com/citations?user=JydqDdEAAAAJ&hl=en" +affiliations: + - name: "Cognitive Robotics, TU Delft" + url: "/" +end_date: 2024-08-31 # end date if ended, approximated if not sure. Just for display purposes and ordering. +# This is the short project description, displayed in the project's card" +description: "Navigation Among Movable Obstacles (NAMO) poses a challenge for traditional path-planning methods when obstacles block the path, requiring push actions to reach the goal. +We propose a framework that enables movability-aware planning to overcome this challenge without relying on explicit obstacle placement. +Our framework integrates a global Semantic Visibility Graph and a local Model Predictive Path Integral (SVG-MPPI) approach to efficiently sample rollouts, taking into account the continuous range of obstacle movability. A physics engine is adopted to simulate the interaction result of the rollouts with the environment, and generate trajectories that minimize contact force. +In qualitative and quantitative experiments, SVG-MPPI outperforms the existing paradigm that uses only binary movability for planning, achieving higher success rates with reduced cumulative contact forces." +cover_image: /assets/images/msc_projects/24_JorisWeeda_SVGMPPI/img_simplified_svg_mppi_overview.jpg # Image displayed in the project's card, make it aspect ratio 1x1 (square) for best results, and keep it a reasonable size (like 1-2MB). Can also be a gif +links: # If you have other website for the project, github repos, datasets, etc. put it here. You can also add an icon from https://icons.getbootstrap.com/ + - name: Thesis + url: "https://repository.tudelft.nl/person/Person_728a81fc-4261-4fd7-ab1d-e5c161e1bbd7" + - name: Code + icon: bi-github + url: "https://github.com/tud-amr/SVG-MPPI" +--- + + + + + + + +
+

Summary

+

+ Navigation Among Movable Obstacles (NAMO) poses a challenge for traditional path-planning methods when obstacles block the path, requiring push actions to reach the goal. + We propose a framework that enables movability-aware planning to overcome this challenge without relying on explicit obstacle placement. + Our framework integrates a global Semantic Visibility Graph and a local Model Predictive Path Integral (SVG-MPPI) approach to efficiently sample rollouts, taking into account the continuous range of obstacle movability. A physics engine is adopted to simulate the interaction result of the rollouts with the environment, and generate trajectories that minimize contact force. + In qualitative and quantitative experiments, SVG-MPPI outperforms the existing paradigm that uses only binary movability for planning, achieving higher success rates with reduced cumulative contact forces. +

+ + +
+

Overview

+ +
+
+
+ Image 1 +
+
+
+

+ An overview of the proposed SVG-MPPI architecture where the SVG provides a weighted graph with efficient node placement around movable obstacles along which a lowest-effort path can be found. The generated set of waypoints guides the MPPI control strategy to efficiently sample rollouts around movable obstacles. If during interaction an obstacle is considered non-movable, the movability estimation gets updated and the path is replanned. Snapshots of a real-world example are shown on the left where the red star indicates the goal location and the masses of the obstacles are (A): 25 kg, (B): 20 kg, (C): 5 kg. +

+
+ + +
+

Example

+
+
+
+ GIF 1 +
+
+
+
diff --git a/_msc_projects_finished/25_DanningZhao_MultiagentMPC.html b/_msc_projects_finished/25_DanningZhao_MultiagentMPC.html new file mode 100644 index 0000000..201bb66 --- /dev/null +++ b/_msc_projects_finished/25_DanningZhao_MultiagentMPC.html @@ -0,0 +1,70 @@ +--- +title: "Motion planning for mobile manipulators in +multi-agent settings using MPC" +authors: + - name: "Danning Zhao" + url: "/" + - name: "Saray Bakker" + url: "https://scholar.google.com/citations?user=kAlAUFkAAAAJ&hl=nl" + - name: "Javier Alonso-Mora" + url: "https://scholar.google.com/citations?user=JydqDdEAAAAJ&hl=en" +affiliations: + - name: "Cognitive Robotics, TU Delft" + url: "/" +end_date: 2024-01-13 # @Danning, adapt this date if you are ready to publish the page, end date if ended, approximated if not sure. Just for display purposes and ordering. +# This is the short project description, displayed in the project's card" +description: "This thesis investigates motion planning via Model Predictive Control for mobile manipulators in multi-agent settings. +The goal is to generate collision-free whole-body motions for mobile manipulators while avoiding collisions with other agents. +This page is still in progress, stay tuned!" +cover_image: /assets/images/msc_projects/25_DanningZhao_MultiagentMPC/rss-demo.png # Image displayed in the project's card, make it aspect ratio 1x1 (square) for best results, and keep it a reasonable size (like 1-2MB). Can also be a gif +links: # If you have other website for the project, github repos, datasets, etc. put it here. You can also add an icon from https://icons.getbootstrap.com/ + - name: Code + icon: bi-github + url: "https://github.com/tud-amr" +--- + + + + + + + +
+

Summary

+

+ This page is still in progress, stay tuned! +

+ + +
+ + + + +
+ + +
+ +
diff --git a/assets/images/msc_projects/24_JorisWeeda_SVGMPPI/demonstration.gif b/assets/images/msc_projects/24_JorisWeeda_SVGMPPI/demonstration.gif new file mode 100644 index 0000000..6bd35e5 Binary files /dev/null and b/assets/images/msc_projects/24_JorisWeeda_SVGMPPI/demonstration.gif differ diff --git a/assets/images/msc_projects/24_JorisWeeda_SVGMPPI/img_simplified_svg_mppi_overview.jpg b/assets/images/msc_projects/24_JorisWeeda_SVGMPPI/img_simplified_svg_mppi_overview.jpg new file mode 100644 index 0000000..07a9f1f Binary files /dev/null and b/assets/images/msc_projects/24_JorisWeeda_SVGMPPI/img_simplified_svg_mppi_overview.jpg differ diff --git a/assets/images/msc_projects/25_DanningZhao_MultiagentMPC/rss-demo.png b/assets/images/msc_projects/25_DanningZhao_MultiagentMPC/rss-demo.png new file mode 100644 index 0000000..249426b Binary files /dev/null and b/assets/images/msc_projects/25_DanningZhao_MultiagentMPC/rss-demo.png differ