Wed, Feb 06, 2019 @ 11:00 AM - 12:00 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Ran Dai, Ohio State University
Talk Title: Planning and Decision-Making for Energy Efficient and Sustainable Autonomous Systems
Abstract: Many autonomous systems will benefit from prolonged operational time and reduced power consumption in a variety of long-duration missions, ranging from terrestrial operating domain to interplanetary space exploration. Due to limited power capacity, dynamic operating environments, complex system behaviors, and strict mission constraints, it is challenging to realize full autonomy with capabilities of sustained power supply and energy efficient operations. Without human intervention, real-time planning and decision-making, including both motion planning and logic/reasoning decisions, play a critical role in assuring the reliability and performance of such systems toward accomplishing the mission objectives.
This talk will present our work on developing vision-based energy awareness, sophisticated modeling approach, highly implementable optimization algorithms, and machine learning based auto-tuning method that collectively contribute to advanced planning and decision-making strategies for energy efficient and sustainable autonomous systems. Applications in two types of autonomous systems will be discussed. One is solar-powered ground robot that harvests energy from the environment and charges the storage batteries as backup to extend the endurance time or realize persistent operations. The other type of application focuses on space vehicles in complex missions involving multiphase or hybrid operations where onboard propellant is limited and timely ground support is unavailable. The overall objective of real-time planning and decision-making for both types of autonomous systems is to realize high-level autonomy in energy harvesting and utilization under dynamic environments, complex operations, and mission constraints. Results obtained in virtual simulations are verified in real-world environments or experimental platforms that mimic the mission challenges, leading to a synthesized theoretical and experimental framework for evaluating improved performance of this transformational technique.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Audiences: Everyone Is Invited
Contact: Tessa Yao