Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
STATISTICAL COMPARISON OF DIFFUSION POLICIES AND EXPLICIT BEHAVIOR CLONING FOR ROBOTIC MANIPULATION
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Statistics.
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Robotic manipulation policies are often trained with limited expert data, in complex actionspaces, and deployed under environmental variability. This thesis compares explicit BehaviorCloning (BC) and Diffusion Policy (DP) on benchmark tasks from the ManiSkill3 framework,and examines their performance. BC offers a lightweight, one-step regression approach but suffers from covariate shift and fails to capture multimodal action distributions. DP frames policylearning as a conditional denoising diffusion process, yielding robust, multimodal action trajectories at the cost of slower inference. DP consistently outperforms BC in sample efficiency, tasksuccess rate, and generalization to novel environments across varying demonstration set sizes(100–600) and two manipulation tasks (pick-and-place and cube stacking). However, DP’s inference speed (≈17 Hz) limits its use in high-frequency control, whereas BC achieves >1,700Hz. These results show the trade-off between accuracy and real-time feasibility.

Place, publisher, year, edition, pages
2025. , p. 27
Keywords [en]
Imitation learning, Diffusion Policy, Diffusion Models
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:uu:diva-562587OAI: oai:DiVA.org:uu-562587DiVA, id: diva2:1978992
Educational program
Master Programme in Statistics
Supervisors
Examiners
Available from: 2025-06-30 Created: 2025-06-29 Last updated: 2025-06-30Bibliographically approved

Open Access in DiVA

fulltext(10589 kB)577 downloads
File information
File name FULLTEXT01.pdfFile size 10589 kBChecksum SHA-512
7c1a7d0fb48d8f73b012696e4eec59be3faadec234d9fb31b79e363bca924e0639ae4b98f3ab8a371752081ebf9e69076efcad56810b4557f9d5bbe9877f7846
Type fulltextMimetype application/pdf

By organisation
Department of Statistics
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 577 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 354 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf