Sachithra Hemachandra
Massachusetts Institute of Technology, University of Edinburgh
Papers
11
Total Citations
347
H-Index
10
About
Sachithra Hemachandra is a pioneering researcher at the intersection of robotics, natural language processing, and human-robot interaction, with a particular focus on enabling robots to understand and act upon human language in real-world environments. His most influential work addresses one of robotics' fundamental challenges: allowing robots to interpret natural language directions and build meaningful spatial representations of unfamiliar surroundings. Hemachandra's most cited contribution, "Learning Models for Following Natural Language Directions in Unknown Environments" (2015, 67 citations), exemplifies his core mission — making robots intuitive collaborators for everyday human settings. His early work on narrated guided tours (2011, 55 citations) laid important groundwork by demonstrating that robots could autonomously follow human guides while interpreting spoken language and spatial context. Complementing this, his research on semantic mapping from natural language descriptions (2013, 46 citations) advanced how robots construct human-centric environmental models. Through frameworks like Generalized Grounding Graphs and information-theoretic dialog systems, Hemachandra has consistently pushed toward robots that don't merely receive commands but engage meaningfully with human knowledge. With over 340 cumulative citations spanning more than a decade, his body of work represents a sustained and impactful contribution to making intelligent robots genuinely accessible to non-expert users.
Research Focus
Key Achievements
Top Papers
- 1
- 2Following and interpreting narrated guided tours55 citations · 2011
- 3Inferring Maps and Behaviors from Natural Language Instructions54 citations · 2015
- 4Learning Semantic Maps from Natural Language Descriptions46 citations · 2013
- 5
- 6
- 7A summary of team MIT's approach to the virtual robotics challenge19 citations · 2014
- 8Information-theoretic dialog to improve spatial-semantic representations18 citations · 2015
- 9
- 10