<aside> ⚠️ This is an Experimental Feature; Please carefully read the limitation section. You may use it only for customer projects if it suits your particular setup and requirements.

</aside>

Teaser

https://www.youtube.com/watch?v=exQV2XrGFLA&ab_channel=NativeRobotics

(https://www.youtube.com/watch?v=exQV2XrGFLA&ab_channel=NativeRobotics)

Benefits

• Our motion planning algorithm increases cycle-time speed to the absolute maximum. We can reach 10 cycles per minute on average on the UR robot. (regular trajectories maximum is ~8)
• At the same time, the motion will be significantly smoother, which will increase the Robot's lifetime, as well as all mechanics around - from column to suction cups
• +20% energy efficient for both robot and vacuum energy consumption
• Optimal Trajectories automatically avoid all collisions, which makes any setup simple, fast, and efficient, even if you have obstacles and tight walls
• Optimal Trajectories automatically avoid all robot’s kinematics and dynamics issues - linear motion, singularities, blends - forget about.

How it works

We calculate trajectories by solving optimization equations. We consider all known obstacles, Joints, Accelerations, and Jerk limits altogether. As a result, we have a time-space spline.

• The Trajectory is a spline for a particular Task.

• The Task has a set of parameters

  • start and stop poses, intermediate waypoints (for example, box enter/exit settings, pallet approach vector)
  • equipment (robot, gripper, column, frame)
  • scene geometry (conveyor, pallets, feeders positions, boxes)
  • box parameters - weight, size, label direction
  • some other settings

  All the parameters above form Task Signature

At every step (next box), we calculate the current task signature and look for a stored trajectory with the same signature. If the signature is found, the trajectory will be executed. If not found, a regular trajectory will be executed, and the task will be sent for planning.

Planning is going in parallel, so the robot will start with regular trajectories for unknown setups. The optimal trajectory will be stored in the PC as soon as it is calculated.