You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
The franka_ros package is currently included as a submodule due to pending features and fixes awaiting integration into the upstream repository. To maintain compatibility with our specific use case, we rely on a custom branch located here. This branch contains several pull requests (PRs) essential for seamless operation but has yet to be merged into the upstream [develop] branch (https://github.com/frankaemika/franka_ros/tree/develop). Below, we'd like to list the required PRs and some optional enhancements.
Gripper PID gains need improvement for the /franka_gripper/gripper_action/goal Action to set the gripper width accurately when the gripper is vertical (see this and this comment).
Additionally, there is a need to enhance the functionality of the /franka_gripper/gripper_action/goal action. The gripperAction currently has a limitation—it can only grasp objects when the gripper width is explicitly specified. On the other hand, the grasp action can grasp things but cannot set a desired gripper width. In reinforcement learning, it would be advantageous for the robot to autonomously learn and set the gripper width while grasping objects, even without prior knowledge of the object size.
Is your feature request related to a problem? Please describe.
The franka_ros package is currently included as a submodule due to pending features and fixes awaiting integration into the upstream repository. To maintain compatibility with our specific use case, we rely on a custom branch located here. This branch contains several pull requests (PRs) essential for seamless operation but has yet to be merged into the upstream [develop] branch (https://github.com/frankaemika/franka_ros/tree/develop). Below, we'd like to list the required PRs and some optional enhancements.
Required Pull Requests
set_franka_model_configuration
service frankaemika/franka_ros#226: Needed to allow users to set the robot joint positions.put_robot_in_world
launch file to start Gazebo using the dart physics engine. This engine is preferred when doing effort control since it is more stable than the ODE physics engine (see franka_ros/issues/160 for more information).tau_ext
internal controller bug frankaemika/franka_ros#228: Necessary to correct the external force calculation, which currently contains errors in the upstream (Issue #364).set_franka_model_configuration
service frankaemika/franka_ros#226.Nice to Have Enhancements
franka_gazebo
andfranka_control
.Some upstream problems that still exist and negatively affect this project
/franka_gripper/gripper_action/goal
Action to set the gripper width accurately when the gripper is vertical (see this and this comment)./franka_gripper/gripper_action/goal
action. The gripperAction currently has a limitation—it can only grasp objects when the gripper width is explicitly specified. On the other hand, the grasp action can grasp things but cannot set a desired gripper width. In reinforcement learning, it would be advantageous for the robot to autonomously learn and set the gripper width while grasping objects, even without prior knowledge of the object size.Proposed Solution
Once all the mentioned PRs have been successfully merged into the upstream repository, we can use the official binary package for
franka_ros
.The text was updated successfully, but these errors were encountered: