3 Challenge Problems with Cyber Physical Systems and IoT

Add to your list(s) Download to your calendar using vCal

• Prof. Rahul Mangharam, Dept. of Electrical and Systems Engineering, School of Engineering and Applied Science, University of Pennsylvania
• Monday 18 July 2016, 11:00-12:00
• Computer Science, The Sloman Lounge (UG).

If you have a question about this talk, please contact Lars Kunze.

Speaker’s homepage: http://www.seas.upenn.edu/~rahulm/

Abstract:

I will present 3 challenge problems where computation and communication are tightly coupled to control large, complex and “messy” plants. These span safety-critical domains of medical devices, energy-efficient buildings, and autonomous vehicles.

1. Medical Devices – From Verified Models to Verified Code The design of bug-free and safe software is challenging, especially in complex implantable devices that control and actuate organs whose response is not fully understood. Safety recalls of pacemakers and implantable cardioverter defibrillators between 1990-2000 affected over 600,000 devices, 41% of those were due to firmware issues. I will describe our efforts to develop synthetic clinical trials to go from 100’s of real patient signals, map them to our heart models, perturb the models to generate 10,000’s of heart models across a range of conditions and then feed them for closed-loop evaluation with medical devices. Such computational modeling and simulation of medical medical devices in the closed-loop context of the physiology we are able to provide regulatory-grade evidence and insights prior to conducting an expensive clinical trial.

2. Energy Systems – Data Predictive Control In the US, energy prices have summer peaks that are over 32x their average prices and winter peaks that are 86x. How can buildings respond to massive swings in energy prices at fast time scales? Demand response (DR) is becoming increasingly important as the volatility on the grid continues to increase. Current DR approaches are completely manual and rule-based or involve deriving first principles based models that are extremely cost and time prohibitive to build. I will describe our recent efforts on the problem of data-driven end-user DR for large buildings that involves predicting the demand response baseline, evaluating fixed rule based DR strategies and synthesizing DR control actions.

3. Autonomous Systems – Plan Verification and Execution Autonomous vehicles have already driven millions of miles on public roads, but even the simplest scenarios, such as a lane change maneuver, have not been certified for safety. This is a significant problem as the insurance liability of autonomous vehicles currently is entirely on the manufacturer as there is no systematic method to bound and minimize the risk of decisions made by the vehicle’s decision controller. I will describe APEX , a tool for autonomous vehicle plan verification and execution across a variety of driving scenarios.

Host: Dr. David Parker

This talk is part of the Artificial Intelligence and Natural Computation seminars series.

This talk is included in these lists:

• Artificial Intelligence and Natural Computation seminars
• Computer Science Departmental Series
• Computer Science Distinguished Seminars
• Computer Science, The Sloman Lounge (UG)
• computer sience

Note that ex-directory lists are not shown.