Trevor Ablett

University of Toronto

Papers

4

Total Citations

25

H-Index

4

About

Trevor Ablett is a roboticist advancing the frontier of contact-rich manipulation through imitation learning and multimodal sensing. His research centers on enabling robots to perform dexterous tasks involving relative motion—like slipping and sliding—by integrating visuotactile feedback. In his most cited work, "Multimodal and Force-Matched Imitation Learning With a See-Through Visuotactile Sensor" (9 citations), Ablett demonstrates how a transparent tactile sensor can be combined with force-matching to teach robots complex contact-rich behaviors. He also addresses a critical limitation of adversarial imitation learning in "Learning From Guided Play" (7 citations), showing that simple auxiliary tasks can dramatically improve exploration during training. His work on "Learning Sequential Latent Variable Models from Multimodal Time Series Data" (5 citations) tackles the challenge of modeling temporal dependencies across sensory streams. Additionally, "Seeing All the Angles" (4 citations) explores multiview visuomotor policies for mobile manipulation platforms. Collectively, Ablett’s contributions are shaping how robots learn from demonstration in unstructured, contact-intensive environments—paving the way for more adaptable and physically capable robotic systems.

Research Focus

Key Achievements

4
H-Index
4
Papers
25
Total Citations
6
Avg Citations/Paper
🏆 Most Cited Paper
Multimodal and Force-Matched Imitation Learning With a See-Through Visuotactile Sensor
9 citations · 2024
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 9
🏛 Institutions: University of Toronto

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago