Navigation based on liability constraints
A navigation system includes a processing device programmed to receive, from an image capture device, at least one image of an environment of the host vehicle; determine, based on at least one driving policy, a navigational action for accomplishing a navigational goal of the host vehicle; analyze the at least one image to identify a target vehicle; test the navigational action against at least one accident liability rule for determining potential accident liability for the host vehicle relative to the target vehicle; if the test indicates that potential accident liability exists for the host vehicle if the navigational action is taken, then cause the host vehicle not to implement the navigational action; and if the test indicates that no accident liability would result for the host vehicle if the navigational action is taken, then cause the host vehicle to implement the navigational action.
1. A system for navigating a host vehicle, the system comprising:
at least one processing device programmed to:
receive, from an image capture device, at least one image representative of an environment of the host vehicle;
receive from at least one sensor an indicator of a current navigational state of the host vehicle;
determine, based on analysis of the at least one image and based on the indicator of the current navigational state of the host vehicle, that a collision between the host vehicle and one or more objects is unavoidable;
determine, based on at least one driving policy, a first planned navigational action for the host vehicle involving an expected collision with a first object and a second planned navigational action for the host vehicle involving an expected collision with a second object;
test the first and second planned navigational actions against at least one accident liability rule for determining potential accident liability;
if the test of the first planned navigational action against the at least one accident liability rule indicates that potential accident liability exists for the host vehicle if the first planned navigational action is taken, then cause the host vehicle not to implement the first planned navigational action; and
if the test of the second planned navigational action against the at least one accident liability rule indicates that no accident liability would result for the host vehicle if the second planned navigational action is taken, then cause the host vehicle to implement the second planned navigational action.
2. The system of claim 1 , wherein at least one of the first and second objects includes another vehicle.
3. The system of claim 1 , wherein at least one of the first and second objects includes a non-vehicle object.
4. The system of claim 1 , wherein the at least one accident liability rule includes a following rule defining a distance behind a target vehicle within which the host vehicle may not proceed without a potential for accident liability.
5. The system of claim 1 , wherein the at least one accident liability rule includes a leading rule defining a distance forward of a target vehicle within which the host vehicle may not proceed without a potential for accident liability.
6. The system of claim 1 , wherein the at least one driving policy is implemented by a trained system, which is trained based on the at least one accident liability rule.
7. A method for navigating a host vehicle, the method comprising:
receiving, from an image capture device, at least one image representative of an environment of the host vehicle;
receiving from at least one sensor an indicator of a current navigational state of the host vehicle;
determining, based on analysis of the at least one image and based on the indicator of the current navigational state of the host vehicle, that a collision between the host vehicle and one or more objects is unavoidable;
determining, based on at least one driving policy, a first planned navigational action for the host vehicle involving an expected collision with a first object and a second planned navigational action for the host vehicle involving an expected collision with a second object;
testing the first and second planned navigational actions against at least one accident liability rule for determining potential accident liability;
if the test of the first planned navigational action against the at least one accident liability rule indicates that potential accident liability exists for the host vehicle if the first planned navigational action is taken, then causing the host vehicle not to implement the first planned navigational action; and
if the test of the second planned navigational action against the at least one accident liability rule indicates that no accident liability would result for the host vehicle if the second planned navigational action is taken, then causing the host vehicle to implement the second planned navigational action.
8. The method of claim 7 , wherein at least one of the first and second objects includes another vehicle.
9. The method of claim 7 , wherein at least one of the first and second objects includes a non-vehicle object.
10. The method of claim 7 , wherein the at least one accident liability rule includes a following rule defining a distance behind a target vehicle within which the host vehicle may not proceed without a potential for accident liability.
11. The method of claim 7 , wherein the at least one accident liability rule includes a leading rule defining a distance forward of a target vehicle within which the host vehicle may not proceed without a potential for accident liability.
12. The method of claim 7 , wherein the at least one driving policy is implemented by a trained system, which is trained based on the at least one accident liability rule.
13. A vehicle having at least one processing device programmed to perform operations comprising:
receiving, from an image capture device, at least one image representative of an environment of the host vehicle;
receiving from at least one sensor an indicator of a current navigational state of the host vehicle;
determining, based on analysis of the at least one image and based on the indicator of the current navigational state of the host vehicle, that a collision between the host vehicle and one or more objects is unavoidable;
determining, based on at least one driving policy, a first planned navigational action for the host vehicle involving an expected collision with a first object and a second planned navigational action for the host vehicle involving an expected collision with a second object;
testing the first and second planned navigational actions against at least one accident liability rule for determining potential accident liability;
if the test of the first planned navigational action against the at least one accident liability rule indicates that potential accident liability exists for the host vehicle if the first planned navigational action is taken, then causing the host vehicle not to implement the first planned navigational action; and
if the test of the second planned navigational action against the at least one accident liability rule indicates that no accident liability would result for the host vehicle if the second planned navigational action is taken, then causing the host vehicle to implement the second planned navigational action.
14. The vehicle of claim 13 , wherein at least one of the first and second objects includes another vehicle.
15. The vehicle of claim 13 , wherein at least one of the first and second objects includes a non-vehicle object.
16. The vehicle of claim 13 , wherein the at least one accident liability rule includes a following rule defining a distance behind a target vehicle within which the host vehicle may not proceed without a potential for accident liability.
17. The vehicle of claim 13 , wherein the at least one accident liability rule includes a leading rule defining a distance forward of a target vehicle within which the host vehicle may not proceed without a potential for accident liability.
18. The vehicle of claim 13 , wherein the at least one driving policy is implemented by a trained system, which is trained based on the at least one accident liability rule.