Erfan Aasi

About

Erfan Aasi is a rising researcher at the intersection of robotics, formal methods, and artificial intelligence, whose work focuses on enabling autonomous systems to make safe, interpretable, and efficient decisions in complex, cluttered environments. His most cited paper (2023, 27 citations) introduces a novel Deep Reinforcement Learning (DRL) framework that overcomes the exploration challenges inherent in continuous control for robot navigation. By integrating temporal logic specifications, Aasi’s approach allows robots to reliably navigate through narrow passageways and obstacle-dense spaces, moving beyond the limitations of noisy, reward-sensitive policies. Complementing this, his work on time-series classification (2022, 11 citations) and temporal logic inference (2021) leverages boosted decision trees to create interpretable models for autonomous systems like self-driving cars. These contributions address the critical need for transparency and trustworthiness in AI-driven decision-making, ensuring that predictions and behaviors are not only accurate but also understandable to humans. Aasi’s research is particularly notable for bridging the gap between theoretical formal methods and practical robotic applications, offering scalable solutions for real-world deployment. With a growing citation footprint, he is establishing himself as a key voice in the development of safe, explainable, and robust autonomous systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments From Temporal Logic Specifications

   27 citations · 2023
2. 2
   Classification of Time-Series Data Using Boosted Decision Trees

   11 citations · 2022
3. 3
   Inferring Temporal Logic Properties from Data using Boosted Decision Trees

   4 citations · 2021

Key Collaborators

Contact & Links