Risk prediction on a peer-to-peer network
AssigneeToyota Research Institute, Inc.
InventorsStephen G. McGill, Guy Rosman, Luke S. Fletcher
Life of this patent
Estimating the term…
Abstract
A method for controlling a driving behavior performed by a first agent includes navigating, by the first agent, according to a trajectory and a velocity. The method also includes receiving, from a second agent, a risk identification message identifying a third agent as a potential risk based on the third agent performing a behavior associated with a probability that is less than a threshold. The method further includes autonomously engaging a defensive driving mode in response to receiving the risk identification message. The method still further includes adjusting one or both of the trajectory or the velocity in response to autonomously engaging the defensive driving mode.
Claims20
A method for controlling a driving behavior performed by a first agent, comprising:
- navigating, by the first agent, through an environment according to a trajectory and a velocity;
- receiving, from a second agent, a risk identification message indicating a third agent is a potential risk based on the second agent determining the third agent performed behavior at a first time period, the risk identification message being associated with a probability of an observed behavior at a second time period that is after the first time period, the probability being less than a threshold;
- autonomously engaging a defensive driving mode in response to receiving the risk identification message;
- and
- adjusting one or both of the trajectory or the velocity in response to autonomously engaging the defensive driving mode.
An apparatus for controlling a driving behavior of a first agent, comprising:
- a processor;
- a memory coupled with the processor;
- and
- instructions stored in the memory and operable, when executed by the processor, to cause the apparatus to:
- navigate according to a trajectory and a velocity;
- receive, from a second agent, a risk identification message indicating a third agent is a potential risk based on the second agent determining the third agent performed a behavior at a first time period, the risk identification message being associated with a probability of an observed behavior at a second time period that is after the first time period, the probability being less than a threshold;
- autonomously engage a defensive driving mode in response to the received risk identification message;
- and
- adjust one or both of the trajectory or the velocity in response to the autonomously engaged the defensive driving mode.
A non-transitory computer-readable medium having program code recorded thereon for controlling a driving behavior of a first agent, the program code executed by a processor and comprising:
- program code to navigate according to a trajectory and a velocity;
- program code to receive, from a second agent, a risk identification message indicating a third agent is a potential risk based on the second agent determining the third agent performed a behavior at a first time period, the risk identification message being associated with a probability of an observed behavior at a second time period that is after the first time period, the probability being less than a threshold;
- program code to autonomously engage a defensive driving mode in response to the received risk identification message;
- and
- program code to adjust one or both of the trajectory or the velocity in response to the autonomously engaged the defensive driving mode.
Dependencies are inferred from the claim text.