Thesis Proposals
Send an email to matteo.rossi@polimi.it and livia.lestingi@polimi.it specifying:
the proposal(s) you are interested in
your current grade average
your current career progress (i.e., number of exams yet to be passed)
It is fine if you do not possess the listed skills when starting out, but do factor in the extra time needed to acquire them.
All listed projects, if completed, are eligible for presentation as a thesis with discussant (i.e., "tesi"). Requests to work on a thesis without a discussant (i.e., "tesina") will be evaluated at the discretion of the supervisor.
Proactive Self-adaptation of Assistive Robot Controllers
Polimi has developed a framework for the development of robotic applications in service settings (e.g., hospitals, home assistance, education).
The framework includes a design-time analysis phase that supports the specification of human-machine teaming missions.
Given the specification, requirements for the mission can be proven (e.g., probability of success greater than 0.9,
maximum fatigue of human agents less than 0.5).
However, a number of factors can dynamically change and affect the satisfaction of such requirements. These factors include quantities observable from the external environment as well as configuration parameters of the system that may be controlled at runtime.
This thesis project aims at making robotic applications self-adaptive, that is, able to adjust its controllable parameters automatically at runtime with the goal of maximizing the likelihood of satisfying all the requirements. Self-adaptation shall be proactive, meaning that the system shall be able to forecast possible violations and adapt itself to avoid them. The selected adaptation measure shall be subject to verification to assess its soundness, ensuring the verification result is available within the estimated remaining duration of the mission.
The thesis shall result in a software tool that support the proactive self-adaptation as well as an empirical evaluation of feasibility, and cost-effectiveness using one or more case studies.
References: 10.1016/j.robot.2023.104387
Inspiration: 10.1145/3524844.3528056
Skills: Automata Theory and Formal Modeling; Multiobjective Optimization; Machine Learning; Good Programming Skills (Python).
Compatible M.Sc. Programs: CS, ATM.
Est. Effort: 8(+/-)2 months
However, a number of factors can dynamically change and affect the satisfaction of such requirements. These factors include quantities observable from the external environment as well as configuration parameters of the system that may be controlled at runtime.
This thesis project aims at making robotic applications self-adaptive, that is, able to adjust its controllable parameters automatically at runtime with the goal of maximizing the likelihood of satisfying all the requirements. Self-adaptation shall be proactive, meaning that the system shall be able to forecast possible violations and adapt itself to avoid them. The selected adaptation measure shall be subject to verification to assess its soundness, ensuring the verification result is available within the estimated remaining duration of the mission.
The thesis shall result in a software tool that support the proactive self-adaptation as well as an empirical evaluation of feasibility, and cost-effectiveness using one or more case studies.
References: 10.1016/j.robot.2023.104387
Inspiration: 10.1145/3524844.3528056
Skills: Automata Theory and Formal Modeling; Multiobjective Optimization; Machine Learning; Good Programming Skills (Python).
Compatible M.Sc. Programs: CS, ATM.
Est. Effort: 8(+/-)2 months
Towards AI-based Oracles for Automata Learning
Active automata learning is a long-standing research area targeting the synthesis of minimal Deterministic Finite-state Automata (DFA).
Foundational learning algorithms (e.g., L*) and tools (e.g., the LearnLib library) can be found in the literature.
Well-established techniques rely on the assumption that an omniscient oracle of the System Under Learning (SUL) is available. However, as complex Cyber-Physical systems grow increasingly widespread, it is paramount to challenge the assumption that perfect knowledge about the SUL is feasible in practice. Indeed, novel data-driven automata learning techniques targeting Hybrid Automata or Markov Decision Processes have been recently introduced.
With this thesis proposal, we foster the investigation of the following research issues:
Inspiration: 10.1109/EMSOFT.2015.7318273; 10.1007/978-3-030-30942-8_38
Skills: Automata Theory; Automata Learning; Good Programming Skills (the specific language may vary depending on the chosen technologies)
Compatible M.Sc. Programs: CS.
Est. Effort: 8(+/-)2 months
Well-established techniques rely on the assumption that an omniscient oracle of the System Under Learning (SUL) is available. However, as complex Cyber-Physical systems grow increasingly widespread, it is paramount to challenge the assumption that perfect knowledge about the SUL is feasible in practice. Indeed, novel data-driven automata learning techniques targeting Hybrid Automata or Markov Decision Processes have been recently introduced.
With this thesis proposal, we foster the investigation of the following research issues:
- How do well-established automata learning algorithms (e.g., L*) perform in a realistic scenario, thus with a non-omniscient oracle relying on partial observations of the SUL?
- How can these algorithms be modified/extended to work in a more realistic setup?
- To this end, can an AI-based oracle (e.g., a Neural Network) be exploited?
- Could this setup simultaneously serve the purpose of generating an explainable model of the AI-based oracle?
Inspiration: 10.1109/EMSOFT.2015.7318273; 10.1007/978-3-030-30942-8_38
Skills: Automata Theory; Automata Learning; Good Programming Skills (the specific language may vary depending on the chosen technologies)
Compatible M.Sc. Programs: CS.
Est. Effort: 8(+/-)2 months
Automated Mission Re-Planning for Assistive Robotics Applications
Polimi has developed a framework for developing robotic applications in service settings
(such as hospitals, home assistance, education) that can handle the unpredictability of
human behavior.
The framework includes a design-time analysis phase to estimate the most likely outcome of
the mission (e.g., success vs. failure due to low battery charge) and, subsequently, deploy
(or simulate) the application. Due to the uncertainties in the environment, the outcome observed
at runtime may not match the one estimated offline, thus, requiring a reconfiguration of the mission
before running new simulations.
The reconfiguration is currently performed manually by the framework's user. This thesis project aims to automate the reconfiguration (or "re-planning") phase by developing a tool to compute alternative plans for the user to choose from and automatically repeat the design-time verification.
The thesis outcome should include a solid justification for the chosen re-planning strategy and validation on significant use cases, highlighting the re-planning phase's added value.
References: 10.1016/j.robot.2023.104387
Inspiration: 10.1007/978-3-030-61362-4_20; 10.1145/3341105.3374001
Skills: Automata Theory and Formal Modeling; Planning/Optimization Tools; Basic Programming Skills (the specific language may vary depending on the chosen technologies)
Compatible M.Sc. Programs: CS; ATM.
Est. Effort: 8(+/-)2 months
The reconfiguration is currently performed manually by the framework's user. This thesis project aims to automate the reconfiguration (or "re-planning") phase by developing a tool to compute alternative plans for the user to choose from and automatically repeat the design-time verification.
The thesis outcome should include a solid justification for the chosen re-planning strategy and validation on significant use cases, highlighting the re-planning phase's added value.
References: 10.1016/j.robot.2023.104387
Inspiration: 10.1007/978-3-030-61362-4_20; 10.1145/3341105.3374001
Skills: Automata Theory and Formal Modeling; Planning/Optimization Tools; Basic Programming Skills (the specific language may vary depending on the chosen technologies)
Compatible M.Sc. Programs: CS; ATM.
Est. Effort: 8(+/-)2 months
Game-based Synthesis and Deployment of Robotic Controllers
Pursue is a development framework for service robotic applications in which robotic agents interact with humans and both collaborate
to achieve common goals, such as ''the robot should carry an item without bumping into the humans moving in the ward''.
Pursue applications can be designed effectively using Timed Games and controlled at runtime through game strategies that govern the
collaborative actions of the agents.
The development of Pursue applications follows a two-steps approach whereby the application is first specified by a domain specific language (Pursue-ML) and analyzed for feasibility; and secondly the application is automatically deployed in a realistic scenario (the target robotic platform is TurtleBot).
If the first phase is successful, the application controller, which allows the application to fulfil the desired goal, is created. The deployment phase is realized by automatically translating the controller into executable ROS code and by setting up the ROS nodes that manage the application at runtime.
Possible thesis are related to the following activities:
Inspiration: 10.1016/j.robot.2023.104387, 10.1109/ACCESS.2021.3117852
Skills: Automata Theory and Formal Modeling; ROS and Robotic 3D Simulators; Good Programming Skills (the specific language may vary depending on the chosen technologies)
Compatible M.Sc. Programs: CS; ATM.
Est. Effort: 8(+/-)2 months
The development of Pursue applications follows a two-steps approach whereby the application is first specified by a domain specific language (Pursue-ML) and analyzed for feasibility; and secondly the application is automatically deployed in a realistic scenario (the target robotic platform is TurtleBot).
If the first phase is successful, the application controller, which allows the application to fulfil the desired goal, is created. The deployment phase is realized by automatically translating the controller into executable ROS code and by setting up the ROS nodes that manage the application at runtime.
Possible thesis are related to the following activities:
- improving Pursue-ML to capture more complex forms of collaborations and scenarios;
- improving the translation of game strategies into executable ROS code;
- improving the automatic deployment to create digital-twin based applications in which physical agents operate in the real environment
while virtual ones operate in the CoppeliaSIM virtual scene.
Inspiration: 10.1016/j.robot.2023.104387, 10.1109/ACCESS.2021.3117852
Skills: Automata Theory and Formal Modeling; ROS and Robotic 3D Simulators; Good Programming Skills (the specific language may vary depending on the chosen technologies)
Compatible M.Sc. Programs: CS; ATM.
Est. Effort: 8(+/-)2 months
