A system and method for vehicle energy management are described that take driving context into account to derive suggested vehicle control inputs to reduce energy consumption. Driving context may be based on information including, for example, traffic congestion and/or flow information for a traveled route, road topology information, traffic controls, weather conditions, vehicle characteristics, and other types of driving context information. The driving context may be used to derive suggested control inputs to reduce energy consumption. The suggested control inputs can, for example, be expressed as: a suggested road speed, suggested gear selection, rate of acceleration or rate of deceleration.

A system and method for vehicle energy management are described that take driving context into account to derive suggested vehicle control inputs to reduce energy consumption. Driving context may be based on information including, for example, traffic congestion and/or flow information for a traveled route, road topology information, traffic controls, weather conditions, vehicle characteristics, and other types of driving context information. The driving context may be used to derive suggested control inputs to reduce energy consumption. The suggested control inputs can, for example, be expressed as: a suggested road speed, suggested gear selection, rate of acceleration or rate of deceleration.

A computer-implemented method for performing few-shot imitation is disclosed. The method comprises obtaining at least one set of training data, wherein each set of training data is associated with a task and comprises (i) one of samples of rewards and a reward function, (ii) one of samples of state transitions and a transition distribution, and (iii) a set of first demonstrations, training a policy network embodied in an agent using reinforcement learning by inputting at least one set of first demonstrations of the at least one set of training data into the policy network, and by maximizing a risk measure or an average return over the at least one set of first demonstrations of the at least one set of training data based on respective one or more reward functions or respective samples of rewards, obtaining a set of second demonstrations associated with a new task, and inputting the set of second demonstrations and an observation of a state into the trained policy network for performing the new task.

An electronic device includes a driving part including a first driving wheel and a second driving wheel; a memory storing at least one instruction; and at least one processor operatively coupled with the driving part and the memory, wherein the at least one processor is configured to execute the at least one instruction to: based on detecting an occurrence of an event for stopping the robot while the first driving wheel rotates at a first speed and the second driving wheel rotates at a second speed, control the driving part to stop the robot based on the first speed and the second speed, and wherein the at least one processor may be further configured to execute the at least one instruction to control the driving part to stop the robot by: based on a relation between the first speed and the second speed satisfying a first condition, controlling the driving part such that a proceeding axis of the first driving wheel rotates in a first direction and a proceeding axis of the second driving wheel rotates in a second direction opposite to the first direction, and based on the relation between the first speed and the second speed satisfying a second condition, controlling the driving part such that the first driving wheel and the second driving wheel rotate in different directions at a same speed.

An electronic device includes a driving part including a first driving wheel and a second driving wheel; a memory storing at least one instruction; and at least one processor operatively coupled with the driving part and the memory, wherein the at least one processor is configured to execute the at least one instruction to: based on detecting an occurrence of an event for stopping the robot while the first driving wheel rotates at a first speed and the second driving wheel rotates at a second speed, control the driving part to stop the robot based on the first speed and the second speed, and wherein the at least one processor may be further configured to execute the at least one instruction to control the driving part to stop the robot by: based on a relation between the first speed and the second speed satisfying a first condition, controlling the driving part such that a proceeding axis of the first driving wheel rotates in a first direction and a proceeding axis of the second driving wheel rotates in a second direction opposite to the first direction, and based on the relation between the first speed and the second speed satisfying a second condition, controlling the driving part such that the first driving wheel and the second driving wheel rotate in different directions at a same speed.

Managing sound levels at an IHS, including determining, for each time duration over a first time period, multiple instantaneous sound levels of the time duration of an environment of the IHS; calculating, for each time duration over first time period, an average sound level of the time duration based on the multiple instantaneous sound levels of the time duration; determining, based on the average sound level of each time duration over the first time period, a lowest average first sound level for first time period; setting the lowest average first sound level as an ambient sound level of the environment of the IHS for the first time period; adjusting, for the first time period, a fan speed of a fan based on the ambient sound level of environment such that a noise level of the fan is less than the ambient sound level of environment for the first time period.

Managing sound levels at an IHS, including determining, for each time duration over a first time period, multiple instantaneous sound levels of the time duration of an environment of the IHS; calculating, for each time duration over first time period, an average sound level of the time duration based on the multiple instantaneous sound levels of the time duration; determining, based on the average sound level of each time duration over the first time period, a lowest average first sound level for first time period; setting the lowest average first sound level as an ambient sound level of the environment of the IHS for the first time period; adjusting, for the first time period, a fan speed of a fan based on the ambient sound level of environment such that a noise level of the fan is less than the ambient sound level of environment for the first time period.