Please register today to join others in shaping the Cities of Tomorrow!

Profile

Recent contributions

(7)

Contribution list

Teams

(3) View all

Recent comments

(3) View all

Hi Tom,
Thank you for your message.
As you correctly point out, our system learns a person's routine and identifies 'usual trips' (i.e., those that involve the same pairs of origins/destinations and occur at roughly the same times/days on a regular basis). Once the 'routine' has been established, the system 'anticipates' that a 'usual trip' is going to occur 'soon' and provides information to the user about the viable alternatives to the traditional mode of choice (when relevant).
In order to accomplish this last part (the recommendations for change), the system identifies all 'usual trips' and then determines those that are viable candidates for change (i.e., those trips for which switching to another mode or a combination of modes will result in marginal, if any, increases in the true 'door-to-door' travel time). For example, trips for which driving is clearly the only viable alternative (given the distances and transit services available), will be 'ignored'. On the other hand, those trips for which alternatives are time-competitive will be 'flagged' and alternatives will be provided to the user.
We are working with our scientific team to make the system truly adaptive and dynamic, so that it automatically adjusts travel mode/route recommendations based on (among other things) changes to personal (e.g., wearing high heels or traveling with a child) and environmental (e.g., longer than normal transit delays or rain) contexts.
With respect to the behavior change measured with our pilots, the results are extremely encouraging, as it suggests that truly personalized information alone can be a significant contributing factor to empowering people to make smarter/healthier/more sustainable travel choices.
I hope this information is useful. Please let me know if you have other questions.
Warm regards
Jose

Hi Tom,

Thanks for your message. I think it is great that you will link the Miami comments so people can read more (at their leisure)!

In terms of your question, there are (at least) two parts:

1. Travel estimates by car with current tools assume that you are either being picked up (by a taxi/Uber/Lyft vehicle) right at your doorstep and dropped off at the precise destination, or that your car is available ‘right where you need it’ and can be parked right in front of your destination. For a large proportion of trips, particularly in urban areas, this is simply not true and motorists have to use on-street or off-street parking spaces that are not necessarily 'right where you need them'. Distinguished academics (like Donald Shoup from UCLA) have identified that 'searching for parking' is a significant contributor to both urban congestion and overall (true) journey times. In our own experiments, we have found that the time walking to the car to start the trip, searching for parking, parking the car and walking to the ultimate destination can easily range between 5-15 minutes in weekday daytime hours. If you add that time (which is totally ignored by current tools) to a short trip, all of a sudden walking, cycling and transit can be highly competitive (in terms of time). However, no current tool considers this aspect and incorrectly would show the car as being significantly quicker.

2. Travel estimates on foot/bike are generally based on an average person's speed, which (in our experiments) are much lower than those exhibited by people during commuting periods. As a result, travel times for walk/bike only trips are overestimated. In addition, transit journey times are also affected as travel planning tools can incorrectly assume that a person would 'miss' a transit service by using the average slower walking speeds. The net effect is that the overall transit time would be overestimated.

On the other hand, current travel planning tools ignore transit crowding and assume that a person is able to board the first vehicle that arrives at the station/stop of interest. In many cases, this is simply not true. In one of our experiments, we measured waiting times at a busy tram stop in Melbourne of between 5-13 minutes in the morning peak. Many of those passengers are using the tram for the last segment of their commute, which is generally 0.5-1 mile in length (given the location of offices along that corridor). That delay alone makes walking the quickest form of travel for that last segment for a large number of commuters; however, no current tool correctly estimates that and they ‘recommend’ (based on time comparison) to take the tram.

We have been discussing time as a key decision-making factor. However, research shows that time is only one of many factors that people consider when making choices. Individual travel choices rely on consideration of a much wider set of factors that can be grouped as: 1) travel mode and time/distance for each journey; 2) personal capabilities/medical conditions; and 3) journey experience (time/day, infrastructure quality, route features, land uses, safety, comfort, stress, attire & weather). Current (and even emerging) approaches only address the first factor, thus sharing an inherent incapability to provide holistic recommendations. We are working with Harvard, CSIRO (the leading scientific body in Australia) and other leading research organizations on the other pieces of the puzzle.

I will definitely link with Safe Routes to School if we progress with the idea.

Cheers

Jose

Hello Bob
Thank you for the feedback and the detailed information about federal programs that may be of relevance. At first glance it seems that the programs are primarily focused on infrastructure improvements. However, I will have a closer look to check for potential eligibility.
Thanks again.
Cheers
Jose