Shalu: A Low-Cost, Multilingual Humanoid Robot for Education
Abstract
Humanoid robotics are increasingly applied in education and social contexts, but commercial platforms are costly. Shalu is a home-built humanoid robot by Dinesh Kunwar Patel (an Indian Scientist and Educator) distinguished by its extreme multilingual capability (reportedly 47 languages) and low-cost, recycled-material construction. This paper reviews Shalu's design and software in detail: it's hardware (waste-derived body, sensors, actuators), its AI/ML-driven language understanding and dialogue systems, and its roles in classroom teaching, guiding, and social assistance. We compare Shalu's features to existing social robots, highlight its unique aspects (e.g. highest number of languages, recycle-based build), and discuss challenges (lack of rigorous evaluation, limited mobility, language biases) and future directions (benchmarking, transformer-based NLP, open-source sharing) to guide further research.
Fields of Study & Subjects
Social Robot Interaction and HRI
Multimodal Machine Learning Applications
Robotics and Automated Systems
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 6 January 2026