projects | Mengying Lin

work

ProGround

An online task aware neural field mapping system that supports robust multimodal localization and navigation in open world environments.

Uncertainty-Aware IRL from Suboptimal Demonstrations

Build rewards with a gaussian model to capture uncertainty for inverse reinforcement learning from Suboptimal Demonstrations

Learning to Communicate in Multi-Agent Environments

Investigates the use of communication between agents in collaborative multi-agent environments.

Multi-agent Cable System

Reinforcement learning implementations for cable-driven parallel robots designed for agricultural monitoring and inspection tasks. The project features both single-agent and multi-agent approaches to optimize path planning and coordination in hydroponic farming environments.

Variational Information Maximizing Exploration

Minimal Inplementation of Variational Information Maximizing Exploration (VIME) to improve exploration in reinforcement learning environments with sparse rewards.

Human-in-the-Loop Object-Goal Navigation

A human-aware object-goal navigation framework that enables robots to reach target objects while adapting their motion to respect human personal space in dynamic household environments.