Master's Thesis Projects
This page contains a list of the Master's Thesis Projects that have been finished in the group. The list is sorted by year. Note that the list is not complete, as it is up to the student to create a website for their project.
If you are interested in doing a Master's Thesis Project with us, please check Master's Thesis Proposals.
2024
Pushing Through Clutter With Movability Awareness of Blocking Obstacles
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.
See details and results!
Simultaneous Synthesis and Verification of Neural Control Barrier Functions through Branch-and-Bound Verification-in-the-loop Training
This thesis focuses on Certified Learning based on Control Barrier Functions (CBFs). While learning-based control techniques often outperform classical controller designs, safety requirements limit the acceptance of such methods in many applications. CBFs have been widely used to provide formal safety guarantees for safety-critical systems. However, it is non-trivial to design a CBF. Utilizing neural networks as CBFs has shown great success, but it necessitates their certification as CBFs. In this work, we leverage bound propagation techniques and the Branch-and-Bound scheme to efficiently verify that a neural network satisfies the conditions to be a CBF over the continuous state space. To accelerate training, we further present a framework that embeds the verification scheme into the training loop to synthesize and verify a neural CBF simultaneously.
See details and results!
Current-Based Impedance Control for Mobile Manipulators Without Force/Torque Sensors
This project explores the use of impedance control on mobile manipulators consisting of an off-the-shelf arm and mobile base. The aim is to achieve compliant behavior, enabeling the system to effectively interact with its environment. Impedance control relies on contact information usually obtained from joint torque measurements. However, off-the-shelf robots may lack such sensors, and adding them is costly. Additionally, the robots may not support torque control, limiting the application of impedance control. Thus, this project presents a calibration method that enables the application of impedance control on a current-controlled manipulator. Moreover, it presents to operational modes for interacting with the mobile manipulator.
See details and results!
Motion planning for mobile manipulators in multi-agent settings using MPC
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!
See details and results!2023
Multi-Modal MPPI and Active Inference for Reactive Task and Motion Planning
Task and Motion Planning (TAMP) has made strides in complex manipulation tasks, yet the execution robustness of the planned solutions remains overlooked. In this work, we propose a method for reactive TAMP to cope with runtime uncertainties and disturbances. We combine an Active Inference planner (AIP) for adaptive high-level action selection and a novel Multi-Modal Model Predictive Path Integral controller (M3P2I) for low-level control. This results in a scheme that simultaneously adapts both high-level actions and low-level motions. The AIP generates alternative symbolic plans, each linked to a cost function for M3P2I. The latter employs a physics simulator for diverse trajectory rollouts, deriving optimal control by weighing the different samples according to their cost. This idea enables blending different robot skills for fluid and reactive plan execution, accommodating plan adjustments at both the high and low levels to cope, for instance, with dynamic obstacles or disturbances that invalidate the current plan. We have tested our approach in simulations and real-world scenarios.
See details and results!