U.S. DOT FY 2023 Phase I Pre-Solicitation Q&A
This U.S. DOT Small Business Innovation Research (SBIR) Pre-solicitation Q&A Forum provides small businesses an opportunity to submit clarifying questions on the topics published in the U.S. DOT Fiscal Year (FY) 2023 Phase I Pre-Solicitation. Questions will be answered by the Technical Experts/Topic Authors at the U.S.DOT Operating Administrations during this period. Questions shall be limited to improving the understanding of a particular topic's requirements and should not share proposal ideas nor proprietary information.
- To create a new account or to sign in with an existing account please click on “sign in” located at the top right of the page.
- A new pop-up window will open to make a selection, you can use an existing Google or Facebook account to access the site or you might select to create a new account.
- If you choose to access UserVoice with an existing Google or Facebook account, you will be required to enter your login credentials for Google or Facebook and agree to terms of service.
- If you need to create a new account, click "Create an Account" underneath the password box.
- In the next screen, type in the e-mail and click "Verify E-mail".
- Navigate to your inbox and click the link within the e-mail to verify. The link will be generated by noreply@trymagic.com
- That link will be live for 20 minutes. Once that time elapses, you will have to request another one.
- Navigate back to UserVoice, and you will need to provide your name, a password, and agree to terms of service and storage permissions. Click "Create Account".
- Select the research topic your question is related to from the drop-down menu that appears when you begin typing.
- You may add more detail in the Description box(optional). Do NOT attach any files. The U.S. DOT shall not consider any submitted materials other than questions.
- Enter your e-mail address and password.
- When finished, select “Post idea.” If you registered, you will be able to track responses to your post. Please include only one question or comment per post to help us keep the forum organized.
26 results found
-
Please clarify the scope of 23-FH2 innovation
There are already many commercial solutions available that detect vehicle types/classes, counts, speed, etc. using legacy computations or AI detection from piezo loops, fiber optic sensors, camera images/video, and other WIM stations. Many of the available solutions also provide edge IoT devices that can be powered by solar batteries. It is NOT clear what new innovation this topic is about? Will the innovation be in detection and classification from various sensor/camera data, in deploying algorithms on the edge devices to process big streams of data, in communicating data to the cloud? All of these have already been developed in commercial…
5 votes -
Design Requirement Clarification
Is the requirement for each sensor to integrate an edge computing chip directly, or would a gateway-based approach that locally aggregates and analyzes data be acceptable?
3 votes -
Alternate Hardware Form Factors?
Redesigning a traffic sensor to include an embedded chip often can require a significant non-recuring engineering cost and also alter the cost economics of the sensor (an edge processing chip could add >$30 to the sensor’s retail price). This can prevent commercial adoption of such technology, as products may no longer be price competitive. The cost to develop and produce such a custom embedded chip is also typically several millions of dollars.
In transportation industries such as airports, ports, and rail, other hardware form factors have successfully enabled this use case as well. An ITS example is the Advanced Traffic…
3 votes -
Prototype Training & Testing?
In regard to 23-FH2, what types of data, if any, will be used to test and train the working scaled prototype?
3 votes -
What specific data should be extracted by the algorithm?
What specific data should be extracted as information by the in-situ information extraction computer algorithm?
3 votes -
"low power consuming edge computing chip"
Can you please provide some more clarity about what you mean by "low-power consuming edge computing chip"? Do you have a specific "low-power" requirement (or range) in mind?
3 votes -
Was the edge computing chip already selected?
Was the edge computing chip already selected? If so, are there any further details about it? Question is from the following line: "The vision is to integrate the low-power consuming edge computing chip with the traditional traffic data sensors"
4 votes -
Edge Device Dynamic Location
Does "in situ" explicitly indicate static locations at road infrastructure or could the edge devices be dynamically moving with road users?
4 votes -
Data Types?
In regard to 23-FH2, will the low-power consuming edge computing chip be expected to process only video or will there be other types of data? Further, what is considered a "traditional traffic data sensor"? Are there other sensors the low-power consuming chip will be expected to integrate with?
3 votes -
Communications Aspects of Solicitation
In regard to 23-FH2, will developers also be responsible for designing the communications aspect of this solicitation?
3 votes -
Chip Form Factor?
In regard to 23-FH2, is there an ideal form factor for the low-power consuming edge computing chip?
2 votes -
2 votes
-
2 votes
-
submissions with one of the three solutions
The Notice calls for three solutions 1. low power consuming edge computing chip 2. programing the chip 3. transmitting data. My question is if we have a solution for one of the issues will the proposal be considered and a partnership established to solve the other two issues?
3 votes -
This is for a *new* device, correct?
To clarify: based on reading the various responses, it appears that the main interest here is a new, self-contained, edge-processing sensor system that is primarily video-based but will work with other sensors (e.g., loop sensors, etc.), and which can properly detect the conditions or sense the events described in those various questions (such as counting and discriminating vehicle types, detecting wet/frozen pavement, sensing accident events, etc.).
It is NOT focused on retrofitting all existing traffic cameras or other sensors with an edge computing system. Correct?
1 vote -
What types of events are of interest?
What types of results or analytics are you envisioning produced from the vehicle and micro-mobility counts, classifications processed in situ? What types of events (crash, weather, etc) are of interest? Or are currently detected?
1 vote -
2 votes
-
Topic Clarifications
1) What are the constraints around ‘low-power’ – e.g. <1W, <10W, <100W? What power source is the solution expected to use (mains voltage, solar, etc)?
2) Are the topic authors looking to fuse sensor and video metadata through edge computing, or replace all sensors with only cameras?-
3) Will the topic authors provide sample data sets for video and sensor data to optimize proposed solutions?
4) Are there any specific mounting location boundary conditions on the cameras and compute hardware – e.g. top of a pole, roadside at vehicle level, etc. ?
5) Are the topic authors open to wireless…1 vote -
Current human interaction in traffic management?
What types of "human interference" currently happen via the Transportation Management Centers? Are there specific signals in the current videos that humans are monitoring to take traffic control action?
1 vote -
"real-time" traffic monitoring?
The pre-solicitation mentions "real-time traffic monitoring." What is the time bound of "real-time" in this scenario? What is the expected application or value of the data being "real-time"?
1 vote