+
+
+
+
+
+ 
+
+
+
+
+
+
+ 
+
+
+ Compliant ROS2 Controllers for Learning-Based Manipulation Policies
+Daniel San José Pro
+with Oliver, Ivan Domrachev, Nabil Miri, niklasschlueter, David Alexander, Vidullan, Veit Gemmer, Maximilian Dösch, Johannes Sautier, Ralf Römer, Linus Schwarz, Lev Kozlov, Luka Hofer, AlexD & Bence Magyar
+★222IEEE RAP 2026
+
+ 
+ learnsyslab.github.io/crisp_controllers
+
+
+ learnsyslab.github.io/crisp_controllers
+
+
+CRISP Controllers
+
+
+
+ Motivation · part 2
+ The missing block: a controller that just tracks a stream of poses, compliantly.
+
+
+
+
+
+
+ The robot software stack
+
+
+
+
+
+
+
+
+
+ engineered modules
+
+
+
+
+
+
+
+ Sense
+ image_transport
+ robot_localization
+
+
+
+
+
+ Plan
+ 
Nav2
+ 
+
+ Nav2
+
+
+
+
+
+ Act
+ 
ros2_control
+
+
+ ros2_control
+
+
+
+
+ less code, more weights
+
+
+
+
+
+
+
+ Policy
absorbs perception + planningsparse pose targets · ~10 Hz
+
+
+
+
+ Controller
compliant · real-timethe CRISP block
+
+
+
+CRISP Controllers
+
+
+ Joint control 101 · a starter
+ Drive a joint to a target angle with torque control
+-
+
- A stiffness gain Kp pulls the joint toward its goal angle. +
- A damping gain Kd settles the motion without overshoot. +
- Turn gravity on and the joint sags below its target: nothing in this law holds it up. +
- Task-space control next is the same idea, lifted into Cartesian space. +
+ ττ
torque commanded to a single joint + = + KpKp
joint stiffness gain: how hard the joint is pulled toward its target angle + (qdesq_des
desired joint angle + − qq
measured joint angle) + − KdKd
joint damping gain: resists joint velocity so the motion settles smoothly, without overshoot + q̇q̇
joint velocity +
+ torque commanded to a single joint + = + KpKp
joint stiffness gain: how hard the joint is pulled toward its target angle + (qdesq_des
desired joint angle + − qq
measured joint angle) + − KdKd
joint damping gain: resists joint velocity so the motion settles smoothly, without overshoot + q̇q̇
joint velocity +
+ 
+ more information ↗
learnsyslab.github.io/crisp_controllers · getting started +
+
+ more information ↗learnsyslab.github.io/crisp_controllers · getting started +
+
+
+
+ Kp closes the angle · Kd settles it
+
+
+
+CRISP Controllers
+
+
+
+
+ What shipping changed
+ Open source in practice
+
+
+ Contributors
+Across crisp_controllers, crisp_py, and crisp_gym.
+ 
Daniel San José Pro@danielsanjosepro
+ 
Oliver@OliEfr
+ 
Ivan Domrachev@domrachev03
+ 
Nabil Miri@Nabil-Miri
+ 
niklasschlueter@niklasschlueter
+ 
David Alexander@dmalexa5
+ 
Vidullan@vidullan
+ 
Veit Gemmer@veit1337
+ 
Maximilian Dösch@maxdoesch
+ 
Johannes Sautier@JohannesSautier
+ 
Ralf Römer@ralfroemer99
+ 
Linus Schwarz@Linus-Schwarz
+ 
Lev Kozlov@lvjonok
+ 
Luka Hofer@lukahofer
+ 
AlexD@AlexD15216
+ 
Bence Magyar@bmagyar
+
+ Daniel San José Pro@danielsanjoseproOliver@OliEfrIvan Domrachev@domrachev03Nabil Miri@Nabil-Miriniklasschlueter@niklasschlueterDavid Alexander@dmalexa5Vidullan@vidullanVeit Gemmer@veit1337Maximilian Dösch@maxdoeschJohannes Sautier@JohannesSautierRalf Römer@ralfroemer99Linus Schwarz@Linus-SchwarzLev Kozlov@lvjonokLuka Hofer@lukahoferAlexD@AlexD15216Bence Magyar@bmagyar
+
+ A lot happened after open-sourcing: new robots, PRs, Papers…
+
+
+
+ 
FR3 / Panda
+ 
UR
+ 
DynaArm
+
+ URDynaArm
+
+
+
+ Influential merged PRs
+
+
+ #46Variable Stiffness ControllerIvan Domrachev
+ #47Admittance ControllerIvan Domrachev
+ #57Decoupled admittance MSD integrationNabil Miri
+ #60Parameterize controller and broadcaster topicsDavid Alexander
+
+
+ Related work using CRISP
+-
+
- Failure prediction at runtime for generative robot policies +
- CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion +
- SQ-CBF: Signed Distance Functions for Numerically Stable Superquadric-Based Safety Filtering +
- From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies +
- Enabling Dynamic Tracking in Vision-Language-Action Models via Time-Discrete and Time-Continuous Velocity Feedforward +
+
+CRISP Controllers
+
+
+
+ Thank you.
+
+ End of the tour
+ Thank you.
Questions?
+ Give it a try! Fork it, test it and share your deployments.
+
+ 
+
+
+
+ Scan for docs, install notes, and the repository.
+
+
+
+
+
+
+
+
+