Inventor

KALAKRISHNAN MRINAL

US31 patents

⚠️ This page may combine multiple inventors who share the name “KALAKRISHNAN MRINAL”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

KALAKRISHNAN MRINAL

X DEV LLC

Operating multiple testing robots based on robot instructions and/or environmental parameters received in a request

Real-time determination of object metrics for trajectory planning

Object pose neural network system

Control policies for collective robot learning

Control policies for robotic agents

Machine learning methods and apparatus for robotic manipulation and that utilize multi-task domain adaptation

Operating multiple testing robots based on robot instructions and/or environmental parameters received in a request

Neural network modules

Operating multiple testing robots based on robot instructions and/or environmental parameters received in a request

Robotic control using value distributions

Machine learning methods and apparatus for automated robotic placement of secured object in appropriate location

Generating reinforcement learning data that is compatible with reinforcement learning for a robotic task

Operating multiple testing robots based on robot instructions and/or environmental parameters received in a request

Machine learning methods and apparatus for automated robotic placement of secured object in appropriate location

Real time robot implementation of state machine

Domain adaptation using simulation to simulation transfer

Neural network modules

Object pose neural network system

Action prediction networks for robotic grasping

Robotic control using action image(s) and critic network

GOOGLE LLC

Operating multiple testing robots based on robot instructions and/or environmental parameters received in a request

Selecting actions to be performed by a robotic agent

Using simulation and domain adaptation for robotic control

Object pose neural network system

Machine learning methods and apparatus for robotic manipulation and that utilize multi-task domain adaptation

Domain adaptation using simulation to simulation transfer

Training a policy model for a robotic task, using reinforcement learning and utilizing data that is based on episodes, of the robotic task, guided by an engineered policy

Efficient adaption of robot control policy for new task using meta-learning based on meta-imitation learning and meta-reinforcement learning

GOOGLE INC

Methods and systems for determining and modeling admissible gripper forces for robotic devices

Real-time determination of object metrics for trajectory planning

GDM HOLDING LLC

Domain adaptation using simulation to simulation transfer