Papers
4
Total Citations
23
H-Index
3
About
Harshal Maske’s research lies at the intersection of robotics, machine learning, and human-robot interaction, with a focus on enabling robots to learn, teach, and collaborate in complex, dynamic environments. His work is distinguished by a dual emphasis: developing algorithms for autonomous learning in spatiotemporally varying domains, and advancing the paradigm of robots as instructors rather than mere learners. In his most cited work (2021), Maske introduced evolving Gaussian processes and kernel observers for monitoring and controlling large-scale stochastic phenomena, with applications in agriculture, weather monitoring, and fluid dynamics—a contribution that has garnered 9 citations and addresses critical challenges in distributed sensing and control. Equally innovative is his exploration of “learning to teach,” where he proposes that robots can autonomously learn instructional policies from expert demonstrations and then guide humans through complex tasks, as seen in his 2018 and 2016 papers on excavator-like robots and co-robots. His 2017 work further enriches this by integrating semantic labels and active learning to improve skill transfer. With a growing citation footprint, Maske’s research is notable for redefining the role of robots from passive tools to proactive collaborators and teachers, pushing the boundaries of learning from demonstration and adaptive control.
Research Focus
Key Achievements
Top Papers
- 1
- 2Learning Task-Based Instructional Policy for Excavator-Like Robots9 citations · 2018
- 3Teaching and Learning using Semantic Labels3 citations · 2017
- 4Can Co-robots Learn to Teach?2 citations · 2016