Topic: Terrain Aware Autonomous Ground Navigation in Unstructured Environments Informed by Human Demonstrations
Location: Lester W. Cory Conference Room, Science & Engineering Building (SENG), Room 213A
Zoom Conference Link: Zoom Link
Meeting ID: 3753158123
Passcode: 495427
Abstract:
Mobile robots equipped with the capability to perform autonomous waypoint navigation can replace humans for applications such as humanitarian assistance, nuclear cleanup, reconnaissance, and transportation. In such tasks, the robot must be able to perform complex navigation behaviors accurately and reliably such as the ability to navigate over unstructured terrain and respond to unseen situations, similar to a human. However, to implement complex behaviors beyond obstacle avoidance, many current approaches employ machine learning methods requiring large amounts of labeled data. While simulations can quickly generate large amounts of labeled data, the same cannot be said for real world environments, limiting adoption of mobile robots to complete the aforementioned applications. Moreover, solutions are often brittle, exhibiting poor performance when operating outside of environments beyond where they were designed or trained. Therefore, there is a need for methods which can learn navigation behaviors from limited or unsupervised data while being able to adapt to dynamic scenarios.
To communicate both positive and negative environmental scenarios, roboticists assign rewards (or inversely, costs) to all the relevant environmental features expected. For robots that need to quickly transition between varying unstructured environments, defining rewards prior to understanding all future features is often unachievable as either (i) the robot is unable to perceive the new feature, and (ii) the numerical reward for each feature is unknown. In such scenarios, it is more effective for a human supervisor to provide examples of desired behavior than for a developer to explicitly define it. Therefore, the proposed dissertation focuses on a ground robot's ability to incorporate human demonstrations as a supervisory signal to solve each respective preceding problem by (i) learning a perception model to identify terrains present in the current environment using unlabeled images and (ii) using Bayesian inverse reinforcement learning (B-IRL) to learn the traversal rewards associated with the terrains identified to build cost-maps online for waypoint traversal.
Advisor(s): Dr. Lance Fiondella, Associate Professor, Department of Electrical & Computer Engineering, UMASS Dartmouth
Committee Members:
Dr. Hong Liu, Professor, Department of Electrical & Computer Engineering, UMASS Dartmouth
Dr. Jiawei Yuan, Associate Professor, Department of Computer Information Science, UMASS Dartmouth
Dr. Craig T. Lennon, United States Army Research Laboratory
Dr. Maggie B. Wigness, United States Army Research Laboratory
NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.
*For further information, please contact Dr. Lance Fiondella at 508.999.8596 or via email at lfiondella@umassd.edu.
/filters:quality(80)/prod01/production-cdn-pxl/media/umassdartmouth/news/2022/1-3-300X159.png)
/filters:quality(80)/prod01/production-cdn-pxl/media/umassdartmouth/college-of-engineering/cis-dept/NSF-CPS-image-3-300X179.jpeg)
/filters:quality(80)/prod01/production-cdn-pxl/media/umassdartmouth/news/2021/Lance-Fiondella-3-300X200.jpg)