Method and system for remote assistance of an autonomous agent
A system 100 for remote assistance of an autonomous agent can include and/or interface with any or all of: a sensor suite 110 , a computing system 120 , a communication interface 130 , and/or any other suitable components. The system can further optionally include a set of infrastructure devices 140 , a teleoperator platform 150 , and/or any other suitable components. The system 100 functions to enable information to be exchanged between an autonomous agent and a tele-assist. Additionally or alternatively, the system 100 can function to operate the autonomous agent (e.g., based on remote inputs received from a teleoperator, indirectly, etc.) and/or can perform any other suitable functions.
1. A method comprising:
with an onboard computing system of a vehicle, autonomously controlling the vehicle based on a set of electable policies; and
while autonomously controlling the vehicle based on the set of electable policies:
determining satisfaction of a probability threshold of an impasse occurrence along a target vehicle path, comprising calculating a probability of the impasse occurrence along the target vehicle path;
based on the satisfaction of the probability threshold, providing a set of outputs to a remote assistance platform; and
updating the set of electable policies to include an operator-approved policy determined with the remote assistance platform, wherein the operator-approved policy is received at the onboard computing system via a wireless connection with a latency greater than 50 milliseconds.
2. The method of claim 1 , further comprising updating the target path based on a set of inputs.
3. The method of claim 1 , wherein the operator-approved policy comprises a set of waypoints.
4. The method of claim 3 , wherein the set of outputs provided to the remote assistance platform comprises a set of estimated object parameters associated with an obstacle, wherein the set of waypoints circumvents the obstacle and deviates from the target path.
5. The method of claim 1 , wherein the operator approved policy is determined based on a binary decision by a remote operator.
6. A method for remote assistance of an autonomous agent, comprising:
based on a first set of inputs, determining satisfaction of an event trigger associated with an impasse along a target path of the autonomous agent, comprising calculating a probability of the impasse along the target path;
based on the event trigger satisfaction, providing a set of outputs to a tele-assist platform, the set of outputs comprising a proposed policy which deviates from the target path;
determining a second set of inputs with the tele-assist platform, the second set of inputs associated with a tele-operator-approved policy, wherein the tele-operator-approved policy is received at an onboard computing system of the autonomous agent via a wireless connection with a latency greater than 50 milliseconds;
determining a set of electable policies comprising the tele-operator-approved policy; and
autonomously controlling the vehicle based on the set of electable policies.
7. The method of claim 6 , wherein autonomously controlling the vehicle occurs asynchronously with providing the set of outputs to the tele-assist platform.
8. The method of claim 6 , further comprising updating the target path based on the second set of inputs.
9. The method of claim 6 , wherein the second set of inputs comprises a set of waypoints which circumvent an obstacle.
10. The method of claim 9 , wherein the set of outputs provided to the tele-assist platform comprises a set of estimated object parameters associated with the obstacle.
11. The method of claim 6 , wherein the second set of inputs comprises a binary decision by a tele-operator.
12. The method of claim 11 , wherein the binary decision comprises a tele-operator approval of the proposed policy.
13. The method of claim 6 , wherein controlling the vehicle based on the set of electable policies comprises: based on the first set of inputs, selecting and implementing a policy which differs from the tele-operator-approved policy.
14. The method of claim 6 , wherein the first set of inputs comprises a position estimate and a scenario.
15. The method of claim 6 , wherein the event trigger comprises a time threshold.
16. The method of claim 6 , further comprising: entering a holding pattern prior to determining the second set of inputs.
17. The method of claim 16 , wherein the holding pattern comprises:
stopping the autonomous agent and waiting for tele-operator approval to proceed.
18. A method for remote assistance of an autonomous agent, comprising:
based on a first set of inputs, determining satisfaction of an event trigger associated with a probability threshold of an impasse, comprising calculating a predicted probability of the impasse;
based on the event trigger satisfaction, providing a set of outputs to a tele-assist platform, the set of outputs comprising a proposed policy;
determining a second set of inputs with the tele-assist platform, the second set of inputs comprising a tele-operator approval of the proposed policy, wherein the tele-operator approval of the proposed policy is received at an onboard computing system of the autonomous agent via a wireless connection with a latency greater than 50 milliseconds;
updating the set of electable policies to include the proposed policy based on the tele-operator approval; and
autonomously controlling the vehicle based on the set of electable policies.
19. The method of claim 18 , wherein the event trigger comprises the probability threshold or a time threshold being exceeded.