Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Towards self-reliant robots : skill learning, failure recovery, and real-time adaptation: integrating behavior trees, reinforcement learning, and vision-language models for robust robotic autonomy

Ahmad, Faseeh LU (2025)
Abstract
Robots operating in real-world settings must manage task variability, environmental uncertainty, and failures during execution. This thesis presents a unified framework for building self-reliant robotic systems by integrating symbolic planning, reinforcement learning, behavior trees (BTs), and vision-language models (VLMs).

At the core of the approach is an interpretable policy representation based on behavior trees and motion generators (BTMGs), supporting both manual design and automated parameter tuning. Multi-objective Bayesian optimization enables learning skill parameters that balance performance metrics such as safety, speed, and task success. Policies are trained in simulation and successfully transferred to real robots... (More)
Robots operating in real-world settings must manage task variability, environmental uncertainty, and failures during execution. This thesis presents a unified framework for building self-reliant robotic systems by integrating symbolic planning, reinforcement learning, behavior trees (BTs), and vision-language models (VLMs).

At the core of the approach is an interpretable policy representation based on behavior trees and motion generators (BTMGs), supporting both manual design and automated parameter tuning. Multi-objective Bayesian optimization enables learning skill parameters that balance performance metrics such as safety, speed, and task success. Policies are trained in simulation and successfully transferred to real robots for contact-rich manipulation tasks.

To support generalization, the framework models task variations using gaussian processes, enabling interpolation of BTMG parameters across unseen scenarios. This allows adaptive behavior without retraining for each new task instance.

Failure recovery is addressed through a hierarchical scheme. BTs are extended with a reactive planner that dynamically updates execution policies based on runtime observations. Vision-language models assist in detecting and identifying failures, and in generating symbolic corrections when tasks are predicted to fail.

The thesis concludes with a discussion of future work, including (1) using vision-language-action (VLA) models or diffusion policies to generate new skills on the fly from multimodal inputs, and (2) extending the reactive planner with proactive failure prediction to anticipate and prevent execution errors before they occur. Together, these directions aim to advance robotic systems that are more robust, adaptable, and autonomous. (Less)
Please use this url to cite or link to this publication:
author
supervisor
opponent
  • Prof. Nalpantidis, Lazaros, DTU Technical University of Denmark, Denmark.
organization
publishing date
type
Thesis
publication status
published
subject
keywords
Autonomous Robotics, Behavior Trees, Reinforcement learning, Vision-Language Models, Failure Recovery
pages
258 pages
publisher
Computer Science, Lund University
defense location
Lecture Hall E:1406, building E, Klas Anshelms väg 10, Faculty of Engineering LTH, Lund University, Lund. The dissertation will be live streamed, but part of the premises is to be excluded from the live stream.
defense date
2025-10-10 13:00:00
ISBN
978-91-8104-681-6
978-91-8104-682-3
language
English
LU publication?
yes
id
7fcb2da0-0594-41a4-8050-e9367d0c408b
date added to LUP
2025-09-15 18:53:45
date last changed
2025-09-18 09:23:32
@phdthesis{7fcb2da0-0594-41a4-8050-e9367d0c408b,
  abstract     = {{Robots operating in real-world settings must manage task variability, environmental uncertainty, and failures during execution. This thesis presents a unified framework for building self-reliant robotic systems by integrating symbolic planning, reinforcement learning, behavior trees (BTs), and vision-language models (VLMs).<br/><br/>At the core of the approach is an interpretable policy representation based on behavior trees and motion generators (BTMGs), supporting both manual design and automated parameter tuning. Multi-objective Bayesian optimization enables learning skill parameters that balance performance metrics such as safety, speed, and task success. Policies are trained in simulation and successfully transferred to real robots for contact-rich manipulation tasks.<br/><br/>To support generalization, the framework models task variations using gaussian processes, enabling interpolation of BTMG parameters across unseen scenarios. This allows adaptive behavior without retraining for each new task instance.<br/><br/>Failure recovery is addressed through a hierarchical scheme. BTs are extended with a reactive planner that dynamically updates execution policies based on runtime observations. Vision-language models assist in detecting and identifying failures, and in generating symbolic corrections when tasks are predicted to fail.<br/><br/>The thesis concludes with a discussion of future work, including (1) using vision-language-action (VLA) models or diffusion policies to generate new skills on the fly from multimodal inputs, and (2) extending the reactive planner with proactive failure prediction to anticipate and prevent execution errors before they occur. Together, these directions aim to advance robotic systems that are more robust, adaptable, and autonomous.}},
  author       = {{Ahmad, Faseeh}},
  isbn         = {{978-91-8104-681-6}},
  keywords     = {{Autonomous Robotics; Behavior Trees; Reinforcement learning; Vision-Language Models; Failure Recovery}},
  language     = {{eng}},
  month        = {{09}},
  publisher    = {{Computer Science, Lund University}},
  school       = {{Lund University}},
  title        = {{Towards self-reliant robots : skill learning, failure recovery, and real-time adaptation: integrating behavior trees, reinforcement learning, and vision-language models for robust robotic autonomy}},
  url          = {{https://lup.lub.lu.se/search/files/227932138/Thesis_final_v2.pdf}},
  year         = {{2025}},
}