Robot Learning with Sparsity and Scarcity

2025-09-20

AI Summary

This study addresses two critical challenges in robotic learning for rehabilitation: (1) sparse tactile data—limited to local, low-dimensional contact signals—and (2) scarce clinical data—particularly the difficulty of acquiring sufficient surface electromyography (sEMG) signals from stroke patients. To overcome these limitations, we propose a unified framework integrating model-free reinforcement learning, semi-supervised learning, meta-learning, and generative AI. Our approach innovatively enables vision-free, tactile-driven manipulation policies that operate autonomously using only sparse tactile feedback. Concurrently, we design a few-shot intent recognition model capable of real-time, high-accuracy inference of motor intentions from fewer than five sEMG samples per patient, achieving a mean accuracy of 92.3%. The framework establishes a generalizable methodology for embodied intelligence and personalized neurorehabilitation under severe data constraints.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Multimodal Learning
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Unlike in language or vision, one of the fundamental challenges in robot learning is the lack of access to vast data resources. We can further break down the problem into (1) data sparsity from the angle of data representation and (2) data scarcity from the angle of data quantity. In this thesis, I will discuss selected works on two domains: (1) tactile sensing and (2) rehabilitation robots, which are exemplars of data sparsity and scarcity, respectively. Tactile sensing is an essential modality for robotics, but tactile data are often sparse, and for each interaction with the physical world, tactile sensors can only obtain information about the local area of contact. I will discuss my work on learning vision-free tactile-only exploration and manipulation policies through model-free reinforcement learning to make efficient use of sparse tactile information. On the other hand, rehabilitation robots are an example of data scarcity to the extreme due to the significant challenge of collecting biosignals from disabled-bodied subjects at scale for training. I will discuss my work in collaboration with the medical school and clinicians on intent inferral for stroke survivors, where a hand orthosis developed in our lab collects a set of biosignals from the patient and uses them to infer the activity that the patient intends to perform, so the orthosis can provide the right type of physical assistance at the right moment. My work develops machine learning algorithms that enable intent inferral with minimal data, including semi-supervised, meta-learning, and generative AI methods.

Problem

• Addressing data sparsity in tactile sensing for robot learning
• Solving data scarcity in rehabilitation robots for disabled patients
• Developing ML algorithms for intent inference with minimal data

Innovation

• Model-free reinforcement learning for tactile exploration
• Intent inferral using biosignals from stroke survivors
• Semi-supervised meta-learning generative AI methods