---
_id: '7175'
abstract:
- lang: eng
text: Deep reinforcement learning (RL) policies for robotic control are typically
trained for a single hardware configuration. When a joint locks, the learned mapping
no longer matches the available actuation. This paper investigates whether combining
self-attention with explicit kinematic observations can improve a policy’s adaptability
to varying active-joint configurations. We train a single RL agent to control
a Franka Emika Panda manipulator across different sets of active joints, from
a restricted 4-degree-of-freedom (DOF) mode to the fully redundant 7-DOF configuration.
Instead of fixed-length state vectors, the method processes the active joints
as a variable-length sequence, enriching each joint’s representation with its
relative spatial offset and geometric Jacobian influence. The proposed kinematics-informed
attention architecture reaches a success rate of 82.1% across trained configurations
and 66.6% on unseen configurations, outperforming multilayer perceptron and generic
attention baselines while remaining nearly collision-free. Deployed on a physical
Panda, the simulation-trained agent reaches 79.0% success on the unseen configurations,
closely matching the simulation on the same target schedule (77.0%).
author:
- first_name: Patrick Thomas
full_name: Mayer, Patrick Thomas
id: '244831'
last_name: Mayer
orcid: 0009-0009-6800-1273
orcid_put_code_url: https://api.orcid.org/v2.0/0009-0009-6800-1273/work/227375532
- first_name: Jan
full_name: Rexilius, Jan
id: '245736'
last_name: Rexilius
orcid: 0000-0002-4579-214X
orcid_put_code_url: https://api.orcid.org/v2.0/0000-0002-4579-214X/work/227375533
citation:
alphadin: 'Mayer, Patrick Thomas ;
Rexilius, Jan: Adapting to Variable
Active-Joint Configurations via Kinematics-Informed Attention for Robot Arms.
In: 9th Iberian Robotics Conference (ROBOT) '
ama: 'Mayer PT, Rexilius J. Adapting to Variable Active-Joint Configurations via
Kinematics-Informed Attention for Robot Arms. In: 9th Iberian Robotics Conference
(ROBOT) .'
apa: Mayer, P. T., & Rexilius, J. (n.d.). Adapting to Variable Active-Joint
Configurations via Kinematics-Informed Attention for Robot Arms. In 9th Iberian
Robotics Conference (ROBOT) . Barcelona.
bibtex: '@inproceedings{Mayer_Rexilius, title={Adapting to Variable Active-Joint
Configurations via Kinematics-Informed Attention for Robot Arms}, booktitle={9th
Iberian Robotics Conference (ROBOT) }, author={Mayer, Patrick Thomas and Rexilius,
Jan} }'
chicago: Mayer, Patrick Thomas, and Jan Rexilius. “Adapting to Variable Active-Joint
Configurations via Kinematics-Informed Attention for Robot Arms.” In 9th Iberian
Robotics Conference (ROBOT) , n.d.
ieee: P. T. Mayer and J. Rexilius, “Adapting to Variable Active-Joint Configurations
via Kinematics-Informed Attention for Robot Arms,” in 9th Iberian Robotics
Conference (ROBOT) , Barcelona.
mla: Mayer, Patrick Thomas, and Jan Rexilius. “Adapting to Variable Active-Joint
Configurations via Kinematics-Informed Attention for Robot Arms.” 9th Iberian
Robotics Conference (ROBOT) .
short: 'P.T. Mayer, J. Rexilius, in: 9th Iberian Robotics Conference (ROBOT) , n.d.'
conference:
end_date: 2026-11-20
location: Barcelona
name: '9th Iberian Robotics Conference (ROBOT) '
start_date: 2026-11-18
date_created: 2026-09-21T16:34:09Z
date_updated: 2026-10-21T09:44:11Z
department:
- _id: '102'
keyword:
- Reinforcement Learning
- Robotic Manipulation
- Kinematic Adaptation
- Sim-to-Real Transfer
language:
- iso: eng
project:
- _id: A827C0AA-C7DA-11E9-B0AE-1F4CB252D58D
name: Institute for Building Intelligence
publication: '9th Iberian Robotics Conference (ROBOT) '
publication_status: accepted
quality_controlled: '1'
status: public
title: Adapting to Variable Active-Joint Configurations via Kinematics-Informed Attention
for Robot Arms
type: conference
user_id: '244831'
year: '2026'
...
---
_id: '7174'
abstract:
- lang: eng
text: This paper presents a hybrid control architecture for dynamic robotic picking
tasks. The framework combines a Deep Reinforcement Learning policy for high-level
interception with a dedicated Inverse Kinematics controller for precise terminal
grasping, while mitigating precision limitations of monolithic learning-based
approaches. The framework utilizes a Proximal Policy Optimization agent to approach
moving targets, seamlessly transitioning to an Inverse Kinematics solver that
reduces terminal orientational and positional errors while minimizing cumulative
control effort. To facilitate deployment on physical hardware, a robust sim-to-real
pipeline incorporating system identification, domain randomization, and latency
injection is employed. Experimental results on a physical Franka Emika Panda manipulator
validate this hybrid architecture. The system achieves an 80% success rate in
pick-and-place tasks, compared to 60.8% for unadapted baselines, with no safety-critical
violations such as joint limit breaches or collisions observed during testing.
author:
- first_name: Patrick Thomas
full_name: Mayer, Patrick Thomas
id: '244831'
last_name: Mayer
orcid: 0009-0009-6800-1273
orcid_put_code_url: https://api.orcid.org/v2.0/0009-0009-6800-1273/work/227375528
- first_name: Jan
full_name: Rexilius, Jan
id: '245736'
last_name: Rexilius
orcid: 0000-0002-4579-214X
orcid_put_code_url: https://api.orcid.org/v2.0/0000-0002-4579-214X/work/227375529
citation:
alphadin: 'Mayer, Patrick Thomas ;
Rexilius, Jan: A Hybrid Control
Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real
Transfer. In: 26th International Conference on Control, Automation and Systems
(ICCAS)'
ama: 'Mayer PT, Rexilius J. A Hybrid Control Framework Using Reinforcement Learning
for Dynamic Robotic Manipulation and Sim-to-Real Transfer. In: 26th International
Conference on Control, Automation and Systems (ICCAS).'
apa: Mayer, P. T., & Rexilius, J. (n.d.). A Hybrid Control Framework Using Reinforcement
Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer. In 26th
International Conference on Control, Automation and Systems (ICCAS). Sapporo.
bibtex: '@inproceedings{Mayer_Rexilius, title={A Hybrid Control Framework Using
Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer},
booktitle={26th International Conference on Control, Automation and Systems (ICCAS)},
author={Mayer, Patrick Thomas and Rexilius, Jan} }'
chicago: Mayer, Patrick Thomas, and Jan Rexilius. “A Hybrid Control Framework Using
Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer.”
In 26th International Conference on Control, Automation and Systems (ICCAS),
n.d.
ieee: P. T. Mayer and J. Rexilius, “A Hybrid Control Framework Using Reinforcement
Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer,” in 26th
International Conference on Control, Automation and Systems (ICCAS), Sapporo.
mla: Mayer, Patrick Thomas, and Jan Rexilius. “A Hybrid Control Framework Using
Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer.”
26th International Conference on Control, Automation and Systems (ICCAS).
short: 'P.T. Mayer, J. Rexilius, in: 26th International Conference on Control, Automation
and Systems (ICCAS), n.d.'
conference:
end_date: 2026-10-30
location: Sapporo
name: 26th International Conference on Control, Automation and Systems (ICCAS)
start_date: 2026-10-27
date_created: 2026-09-21T16:30:06Z
date_updated: 2026-10-21T09:43:36Z
department:
- _id: '102'
keyword:
- Reinforcement Learning
- Hybrid Control
- Sim-to-Real
- Robotic Manipulation
- Inverse Kinematics.
language:
- iso: eng
project:
- _id: A827C0AA-C7DA-11E9-B0AE-1F4CB252D58D
name: Institute for Building Intelligence
publication: 26th International Conference on Control, Automation and Systems (ICCAS)
publication_status: accepted
quality_controlled: '1'
status: public
title: A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic
Manipulation and Sim-to-Real Transfer
type: conference
user_id: '244831'
year: '2026'
...