Dynamic routing for self-driving vehicles
View Patent ↗A self-driving vehicle (SDV) can dynamically analyze a sensor view of a surrounding area of the SDV, and a current localization map in order to autonomously operate acceleration, braking, and steering systems of the SDV along a current route to a destination. Upon approaching a decision point along the current route, the SDV can perform a cost optimization to determine whether to diverge from the current route.
1. A self-driving vehicle (SDV) comprising:
acceleration, braking, and steering systems;
a set of sensors generating a sensor view of a surrounding area of the SDV; and
a control system comprising one or more processors executing an instruction set that causes the control system to:
dynamically analyze (i) the sensor view of the surrounding area, and (ii) a current localization map in order to autonomously operate the acceleration, braking, and steering systems along a current route to a destination;
upon approaching a decision point along the current route, perform a cost optimization by:
determining one or more alternative route options that diverge from the current route at the decision point;
determining, from the sensor view, a risk factor for continuing along the current route;
determining, from the sensor view, an additional risk factor for each of the one or more alternative route options; and
determining whether to diverge from the current route based, at least in part, on the risk factor for continuing along the current route and the additional risk factor for each of the one or more alternative route options.
2. The SDV of claim 1 , wherein the executed instruction set further causes the control system to determine the one or more alternative route options that diverge from the current route by:
transmitting a route option inquiry to a backend transport routing system; and
based on the route option inquiry, receiving, from the backend transport routing system the one or more alternative route options that diverge from the current route at the decision point.
3. The SDV of claim 2 , wherein the executed instruction set causes the control system to further perform the cost optimization by (i) determining, from the sensor view, an immediate traffic situation on the current route, and (ii) comparing the immediate traffic situation on the current route with one or more traffic situations corresponding to the one or more alternative route options.
4. The SDV of claim 3 , wherein the backend transport routing system manages routing for a fleet of self-driving vehicles, including the SDV, throughout a given region.
5. The SDV of claim 3 , wherein the executed instruction set further causes the control system to:
transmit a localized traffic context update to the backend transport routing system, the localized traffic context update indicating the immediate traffic situation.
6. The SDV of claim 4 , wherein the executed instruction set further causes the control system to:
receive a route update for the current route from the backend transport routing system based on traffic context data submitted by individual vehicles in the fleet of self-driving vehicles.
7. The SDV of claim 4 , wherein performance of the cost optimization upon approaching the decision point corresponds to routing by the control system based on the dynamic analysis of the sensor view.
8. The SDV of claim 1 , wherein each of the one or more alternative route options is associated with a time delta, and wherein the executed instruction set causes the control system to determine whether to diverge from the current route by (i) determining, from the sensor view, a time delta for continuing along the current route, and (ii) comparing the time delta for continuing along the current route to the time delta for each of the one or more alternative route options.
9. A non-transitory computer readable medium storing instructions that, when executed by one or more processors of a control system for a self-driving vehicle (SDV), cause the control system to:
dynamically analyze (i) a sensor view of a surrounding area of the SDV, and (ii) a current localization map in order to autonomously operate acceleration, braking, and steering systems of the SDV along a current route to a destination; and
upon approaching a decision point along the current route, perform a cost optimization by:
determining one or more alternative route options that diverge from the current route at the decision point;
determining, from the sensor view, a risk factor for continuing along the current route;
determining, from the sensor view, an additional risk factor for each of the one or more alternative route options; and
determining whether to diverge from the current route based, at least in part, on the risk factor for continuing along the current route and the additional risk factor for each of the one or more alternative route options.
10. The non-transitory computer readable medium of claim 9 , wherein the executed instructions cause the control system to determine the one or more alternative route options by:
transmitting a route option inquiry to a backend transport routing system; and
based on the route option inquiry, receiving, from the backend transport routing system, the one or more alternative route options that diverge from the current route at the decision point.
11. The non-transitory computer readable medium of claim 10 , wherein the executed instructions cause the control system to further perform the cost optimization by (i) determining, from the sensor view, an immediate traffic situation on the current route, and (ii) comparing the immediate traffic situation on the current route with one or more traffic situations corresponding to the one or more alternative route options.
12. The non-transitory computer readable medium of claim 11 , wherein the backend transport routing system manages routing for a fleet of self-driving vehicles, including the SDV, throughout a given region.
13. The non-transitory computer readable medium of claim 12 , wherein the executed instructions further cause the control system to:
transmit a localized traffic context update to the backend transport routing system, the localized traffic context update indicating the immediate traffic situation.
14. The non-transitory computer readable medium of claim 12 , wherein the executed instructions further cause the control system to:
receive a route update for the current route from the backend transport routing system based on traffic context data submitted by individual vehicles in the fleet of self-driving vehicles.
15. The non-transitory computer readable medium of claim 12 , wherein performance of the cost optimization upon approaching the decision point corresponds to routing by the control system based on the dynamic analysis of the sensor view.
16. A computer-implemented method of operating a self-driving vehicle (SDV), the method being performed by one or more processors of the SDV and comprising:
dynamically analyzing (i) a sensor view of a surrounding area of the SDV, and (ii) a current localization map in order to autonomously operate acceleration, braking, and steering systems of the SDV along a current route to a destination;
upon approaching a decision point along the current route, performing a cost optimization by:
determining one or more alternative route options that diverge from the current route at the decision point;
determining, from the sensor view, a risk factor for continuing along the current route; and
determining, from the sensor view, an additional risk factor for each of the one or more alternative route options; and
determining whether to diverge from the current route based, at least in part, on the risk factor for continuing along the current route and the additional risk factor for each of the one or more alternative route options.
17. The method of claim 16 , wherein determining the one or more alternative route options that diverge from the current route comprises:
transmitting a route option inquiry to a backend transport routing system; and
based on the route option inquiry, receiving, from the backend transport routing system, the one or more alternative route options that diverge from the current route at the decision point.
18. The method of claim 17 , wherein performing the cost optimization further comprises (i) determining, from the sensor view, an immediate traffic situation on the current route, and (ii) comparing the immediate traffic situation on the current route with one or more traffic situations corresponding to the one or more alternative route options.
19. The method of claim 18 , wherein the backend transport routing system manages routing for a fleet of self-driving vehicles, including the SDV, throughout a given region.