CPS-PI Meeting 2018

file

Visible to the public Maneuver and Data Optimization for High Confidence Testing of Future Automotive Cyber-Physical Systems

Submitted by Ilya V. Kolmanovsky on Tue, 01/22/2019 - 7:37pm. Contributors:

Our research addresses urgent challenges in high confidence testing of automotive systems due to on-going and anticipated introduction of advanced, connected, and autonomous vehicle technologies. We have pursued the development of tools for maneuver and data optimization to determine test trajectories and scenarios to facilitate vehicle testing. Our approaches exploit game theoretic traffic interaction modeling to inform in-traffic relevant trajectories, model-free optimization to identify trajectories falsifying time domain specifications, and the development of Smart Bla

file

Visible to the public Matching Parking Supply to Travel Demand towards Sustainability

Submitted by Michael Zhang on Tue, 01/22/2019 - 7:37pm. Contributors:

Parking can take up a significant amount of the trip costs (time and money) in urban travel. As such, it can considerably influence travelers' choices of modes, locations, and time of travel. The advent of smart sensors, wireless communications, social media and big data analytics offers a unique opportunity to tap parking's influence on travel to make the transportation system more efficient, cleaner, and more resilient. A cyber-physical social system for parking is proposed to realize parking's potential in achieving the above goals.

file

Visible to the public Leveraging Honey Bees as Bio-Cyber Physical Systems

Submitted by Kirstin Petersen on Tue, 01/22/2019 - 7:37pm. Contributors:

The goal of this project is to leverage and improve upon the capabilities of honey bees as agricultural pollinators by incorporating them into Bio-Cyber Physical sistems. Rapid advances are needed to aid a dwindling agricultural, increase crop yield to sustain the growing population, and provide targeted crop care to limit the need for broad pesticide treatments. These challenges may well be addressed by autonomous mobile robots and sensor networks; unfortunately, agricultural landscapes represent vast, complex, and dynamic environments that complicate long term operation.

file

Visible to the public Learning to Walk: Optimal Gait Synthesis and Online Learning for Terrain-Aware Legged Locomotion

Submitted by Anonymous on Tue, 01/22/2019 - 5:50pm. Contributors:

The goal of the proposed research is to advance the science of cyber-physical systems by more explicitly tying sensing, perception, and computing to the optimization and control of physical systems whose properties are variable and uncertain. The CPS platform to be studied is that of a bipedal robot locomoting over granular ground material with uncertain physical properties (sand, gravel, dirt, etc.).

file

Visible to the public Learning with Abandonment

Submitted by rodrigka on Tue, 01/22/2019 - 5:50pm. Contributors:

Consider a demand response provider that wants to learn a personalized policy for each user, but the platform faces the risk of a user abandoning the platform if she is dissatisfied with the actions of the platform. For example, the platform will want to personalize the thermostat control for the user, but faces the risk that the user unsubscribes forever if they are mistreated. We propose a general thresholded learning model for scenarios like this, and discuss the structure of optimal policies.

file

Visible to the public Learning and Teaching Task Specifications from Demonstrations

Submitted by Anonymous on Tue, 01/22/2019 - 5:50pm. Contributors:

Real world applications often naturally decompose into several sub-tasks. In many settings (e.g., robotics) demonstrations provide a natural way to specify the sub-tasks. However, most methods for learning from demonstrations either do not provide guarantees that the artifacts learned for the subtasks can be safely recombined or limit the types of composition available.