Problem
Urban multimodal transportation is complicated:
1. Mode transfers are inefficient.
2. Current routing tools are not designed for multimodal transportation.
3. Static schedules do not reflect real-world conditions.
4. Transport authorities lack tools to analyze multimodal traffic flows.
5. Commuters experience
    1. unreliable mode transfers and line switches,
    2. poor usability and inclusion,
    3. longer wait times.

Solution - Hmaps
We simplify urban multimodal transportation through AI driven multimodal routing, where we,
1. represent transit cities as integrated multimodal transportation networks and
2. use graph neural networks to optimize multimodal routing by explicitly considering
    1. mode transfers,
    2. line switches and
    3. mode specific spatiotemporal aspects.

We design city-specific, public transport focused multimodal routing engines that optimize multimodal transportation.

Hmaps

Org chart

Teams

Offices

Hmaps

Org chart

Teams

Offices

Related companies