Collaborating Authors


AAAI Conferences

Many software systems run on long-lifespan platforms that operate in diverse and dynamic environments. If these software systems could automatically adapt to hardware changes, it would significantly reduce the maintenance cost and enable rapid upgrade. In this paper, we study the problem of how to automatically adapt to sensor changes, as an important step towards building such long-lived, survivable software systems. We address the adaptation scenarios where a set of sensors are replaced by new sensors. Our approach reconstructs sensor values of replaced sensors by preserving distributions of sensor values before and after the sensor change, thereby not warranting a change in higher-layer software. Compared to existing work, our approach has the following advantages: a) exploiting new sensors without requiring an overlapping period of time between new sensors and old ones; b) providing an estimation of adaptation quality; c) scaling to a large number of sensors. Experiments on weather data and Unmanned Undersea Vehicle (UUV) data demonstrate that our approach can automatically adapt to sensor changes with higher accuracy compared to baseline methods.

A smart home mega sensor can track what goes on in a room


Creating a smart home currently requires either linking every connected device one-by-one or adding sensor tags to old appliances to make a cohesive IoT network, but there might be an easier way. Researchers at Carnegie Mellon developed a concept for a hub that, when plugged into an electrical outlet, tracks ambient environmental data -- essentially becoming a sensor that tracks the whole space. With this in hand, savvy programmers can use it to trigger their own connected home routines. The researchers introduced their sensor nexus -- dubbed Synthetic Sensors -- this week at ACM CHI, the human-computer interaction conference. As the video demonstrates, just plug it into a USB wall port and it automatically collects information about its surroundings, uploading it to a cloud back-end over WiFi.

Kicking the Sensing Habit

AI Magazine

Sensor dependency is an affliction that affects an alarming number of robots, and the problem is spreading. In some situations, sensor use is advisable, perhaps even unavoidable. However, there is an important difference between sensor use and sensor abuse. This article lists some of the telltale signs of sensor dependency and reveals the tricks of the trade used on unwitting roboticists by wily sensor pushers.

Tiny sensors inspired by gliding seeds could monitor the environment

New Scientist

Tiny wireless sensors inspired by floating seeds could be used to measure environmental factors such as pH – but they could also have military applications. John Rogers at Northwestern University in Illinois and his colleagues have developed sensors whose shape is modelled on seeds like those of maples that spin or glide down to the ground so they can disperse further.

Maine to Collect Ocean Acidification Data With New Sensors

U.S. News

The Maine Department of Marine Resources said it has installed the three sensors in Boothbay Harbor. The department said the sensors will help researchers get a better understanding of how ocean acidification and dissolved oxygen levels can change the health of the state's marine life and ecosystems.