Towards generalizable motion planning: Efficient and safe learning-based frameworks
| dc.contributor.author | Ghafarian Tamizi, Mehran | |
| dc.contributor.supervisor | Najjaran, Homayoun | |
| dc.date.accessioned | 2025-12-04T23:02:34Z | |
| dc.date.available | 2025-12-04T23:02:34Z | |
| dc.date.issued | 2025 | |
| dc.degree.department | Department of Electrical and Computer Engineering | |
| dc.degree.level | Doctor of Philosophy PhD | |
| dc.description.abstract | Robotic motion planning remains a fundamental challenge in industrial automation, with manipulators offering a clear example of the need for real-time, collision-free, and safe trajectory generation. Traditional planners often face trade-offs among optimality, adaptability, and computational efficiency, limiting their applicability in cluttered and high-dimensional industrial environments. Furthermore, most learning-based planners suffer from poor generalization, requiring retraining when deployed in new scenes or on different robot platforms. This thesis presents two learning-based frameworks designed to address these challenges. First, the Path Planning and Collision Checking Network (PPCNet) is introduced, an end-to-end neural architecture that combines a waypoint generator with a learned collision checker to enable fast, safe, and reliable planning in structured environments. PPCNet is validated in both simulated and real-world bin-picking tasks, demonstrating substantial speedups over classical planners while maintaining path quality. To overcome the generalization limitations of PPCNet, Generalizable and Adaptive Diffusion-Guided Environment-aware Trajectory generation (GADGET) is proposed, a conditional diffusion-based motion planner guided by control barrier functions. GADGET leverages voxel-based scene encoding and goal conditioning to generate safe trajectories across previously unseen environments and robotic arms without retraining. The integration of barrier-function-based guidance enables robust collision avoidance during trajectory generation. Extensive experiments demonstrate that both frameworks achieve real-time planning performance and high success rates, with GADGET offering strong generalization to novel settings. This work highlights the potential of combining deep generative models with adaptable design to create scalable and broadly generalizable motion planners, capable of transferring across diverse environments and robot platforms with minimal modification. | |
| dc.description.scholarlevel | Graduate | |
| dc.identifier.bibliographicCitation | Mehran Ghafarian Tamizi, Marjan Yaghoubi, and Homayoun Najjaran. "A review of recent trend in motion planning of industrial robots." International Journal of Intelligent Robotics and Applications 7, no. 2 (2023): 253-274. | |
| dc.identifier.bibliographicCitation | Mehran Ghafarian Tamizi, Homayoun Honari, Aleksey Nozdryn-Plotnicki, and Homayoun Najjaran. "End-to-end deep learning-based framework for path planning and collision checking: bin-picking application." Robotica 42, no. 4 (2024): 1094-1112. | |
| dc.identifier.bibliographicCitation | Mehran Ghafarian Tamizi, Homayoun Honari, Amir Mehdi Soufi Enayati, Aleksey Nozdryn-Plotnicki, and Homayoun Najjaran. "A Cross-Environment and Cross-Embodiment Path Planning Framework via a Conditional Diffusion Model." arXiv preprint arXiv:2510.19128 (2025). | |
| dc.identifier.uri | https://hdl.handle.net/1828/22945 | |
| dc.language | English | eng |
| dc.language.iso | en | |
| dc.rights | Available to the World Wide Web | |
| dc.subject | Motion Planning | |
| dc.subject | Path Planning | |
| dc.subject | Diffusion Models | |
| dc.subject | Zero-shot Generalization | |
| dc.subject | Collision Avoidance | |
| dc.title | Towards generalizable motion planning: Efficient and safe learning-based frameworks | |
| dc.type | Thesis |