In the rapidly advancing landscape of deep reinforcement learning (RL), recent studies have highlighted vulnerabilities in control policies learned through deep RL. These vulnerabilities raise concerns surrounding adversarial attacks, especially in risk-sensitive domains such as autonomous driving. In these scenarios, the learned policies become susceptible...

­Advanced vehicle control systems (e.g., an electronic stability control system) can greatly reduce accident rates and fatality in accidents. Vehicle control systems in automated vehicles (AVs) are able to ensure vehicle safety in many driving scenarios by cooperating with other advanced perception and path planning systems of the AVs. A typical...

Pressure/force sensors and transducers have wide utility in mechanical, medical and industrial applications, with each industry striving for increased performance. Three key features determine how successful a pressure sensor may be: sensitivity, durability, and cost. Because of their robust and inexpensive nature, transformative electrochemical pressure/force...

Many products, such as medical devices, need a unified way of encoding uniquely-identifying information that can be easily accessed. This can provide traceability to specifications, lot numbers, recalls, etc. This applies to medical devices both in and out of the body as well as many consumer goods. Common codes, such as a UPCs, can only be read if...