normal force

Towards Concept Map Based Free Student Answer Assessment

AAAI Conferences

We propose a concept map based approach to assessing freely generated student responses. The proposed approach is based on a novel automated tuple extraction system, DT-OpenIE, for automatically extracting concept maps from student responses. The DT-OpenIE system is significantly better in terms of concept map quality for assessment purposes than state-of-the-art open information extraction (IE) systems such as Ollie or Stanford as evidenced by our experimental results. The concept map based approach can significantly improve tracking student's mastery level in an automated tutoring environment such as DeepTutor where students interact with the automated tutor using natural language because the concept maps can be used not only to generate a holistic score assessing the accuracy of a student response but also enable diagnostic feedback.

Estimate the Pulling Force of Boston Dynamics' Robo-Dog Army


When Boston Dynamics shares a new robot video, my robophobia levels increase just a little bit. There is something about these robots that get into the uncanny valley for me. This particular video is both fascinating and disturbing. It's fascinating because here are a bunch of robots pulling a truck (not a pickup truck--a real truck). It's disturbing because it shows a BUNCH of robots.

Machine with sticky feet which can can climb up, down, and all around jet engines

Daily Mail - Science & tech

A robot with sticky feet that can climb up and down vertical walls as well as across the ceiling has been created by scientists. Harvard University engineers and Rolls-Royce partnered to make the robot which they say could inspect complex machines in the future. The device could be used in future to identify and maintain jet engines, scientific instruments and even generators. Jet engines can have up to 25,000 individual parts, making regular maintenance a tedious task that can take over a month per engine. Many components are located deep inside the engine and cannot be inspected without taking the machine apart, adding time and costs to maintenance.

How to Run Up a Wall--With Physics!


I can't decide if this looks like something from a super hero movie or from a video game. In this compilation video of crazy stunts, a guy somehow finds a way to bound up between two walls by jumping from one to the other. "Somehow," of course, means with physics: This move is based on the momentum principle and friction. Could you pull it off? But you can at least do the math.

How Much Haptic Surface Data Is Enough?

AAAI Conferences

The Proton Pack is a portable visuo-haptic surface interaction recording device that will be used to collect a vast multimodal dataset, intended for robots to use as part of an approach to understanding the world around them. In order to collect a useful dataset, we want to pick a suitable interaction duration for each surface, noting the tradeoff between data collection resources and completeness of data. One approach frames the data collection process as an online learning problem, building an incremental surface model and using that model to decide when there is enough data. Here we examine how to do such online surface modeling for the initial problem of learning a kinetic friction model. With a long dataset consisting of force, vibration, and speed recorded by a human operator moving a tooling ball end-effector across a flat vinyl surface, we find a good stopping point at 55.4 s.

Getting Up to Speed on Vehicle Intelligence

AAAI Conferences

Our research explores the development of methodology and supporting technology for combining qualitative and semi-quantitative models with measured data to produce readable explanations of vehicle actions. Control systems in the vehicle should be able to give an accurate unambiguous accounting of the events. These explanations will have to be simple enough for users to understand even when subject to cognitive distractions. For example, when the autonomous system takes over suddenly, the driver will ask why. When an accident happens in a car that is co-driven by a person and a machine, police officials, insurance companies, and the people who are harmed will want to know who or what is accountable for the accident. . In this paper, we present preliminary work towards an explanatory diagnostic system for the vehicle. In particular, we present two models that use measured data to initialize parameters, and then propagate symbolic values to produce concise, understandable explanations of vehicle actions that humans will perceive as a causal chain.