We need your help to remedy the problem of potholes! Given acceleration and GPS data collected by volunteers running the StreetBump app on Android smartphones, build a computer program that predicts the location of potholes and other street features.
This is a Reduction-to-Practice Challenge that requires a written proposal and delivery of a working algorithm, source code, and prediction to the Seeker.
The City of Boston has partnered with InnoCentive and researchers at Worcester Polytechnic Institute and the Santa Fe Complex to eliminate the problem of potholes. The Challenge is to predict where potholes and other dangerous street features are located, using data collected by the “StreetBump” application running on volunteers’ Android smart phones. The StreetBump app can collect GPS (Global Positioning System) and acceleration data as people drive throughout the city. From these data, potholes could be identified either after a single pass over a pothole or after repeated passes over the same location, with the presence (or absence) of actual road damage confirmed by the acceleration events that occur at that location.
The City of Boston needs a Solver to deliver a computer algorithm that can accurately identify the location and severity of potholes, given a large and dynamic set of acceleration and position data.
A major award ($22,500) is designated for the best solution(s) that meet the required specifications, from the population of Solvers at large. This major award can be paid out as one award ($22,500) for the best solution or split into two awards for 1st ($15,000) and 2nd ($7,500) place at the sole discretion of the Seeker. A minor award ($2500) is set aside for a Solver who is a Boston city resident or a full-time student at a Boston college or university.
Employees of Liberty Mutual Group or members of an employee’s immediate family, or employees of the City of Boston or members of an employee’s immediate family are not eligible to participate in this Challenge.
A submission to the Challenge should include the following:
1. Detailed description of the proposed Solution, addressing specific Technical Requirements presented in the Detailed Description of the Challenge. This description should be accompanied by a well-articulated rationale that exposes the logic of the algorithmic approach.
2. Source code for a working computer algorithm that predicts the location of potholes and other street features when given acceleration and GPS data in a standardized input format. The algorithm should not rely upon third-party libraries, linked code, or licenses that restrict the scope of the Solution, nor increase the cost of implementation.
The award is contingent upon theoretical evaluation of the submitted Solutions and validation of a working algorithm by the Seeker.
To receive an award, the Solvers will be required to transfer to the Seeker their exclusive Intellectual Property (IP) rights to the solution. While the City of Boston intends to release the solution under a permissive license such as the LGPL (GNU Lesser General Public License), exclusive Intellectual Property rights will transfer to the City of Boston regardless of the eventual licensing.
An InnoCentive RTP (Reduction to Practice) Challenge is a prototype that proves an idea, and is similar to an InnoCentive Theoretical Challenge in its high level of detail. However, an RTP requires the Solver to submit a validated solution, either in the form of original data or a physical sample. Also the Seeker is allowed to test the proposed solution.