Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 1906.07669

A Dynamic Robotic Actuator with Variable Physical Stiffness and Damping

Manuel Aiple·Wouter Gregoor·Andre Schiele
View original source ↗Read source document ↗Export metadata ↓

Abstract

This study is part of research aiming at increasing the range of dynamic tasks for teleoperated field robotics in order to allow operators to use the full range of human motions without being limited by the dynamics of the robotic manipulator. A new variable impedance actuator (VIA) was designed, capable of reproducing motions through teleoperation from precise positioning tasks to highly dynamic tasks. The design requirements based on previous human user studies were a stiffness changing time of 50 ms, a peak output velocity of 20 rad/s and variable damping allowing to suppress undesired oscillations. This is a unique combination of features that was not met by other VIAs. The new design has three motors in parallel configuration: two responsible for changing the VIA's neutral position and effective stiffness through a sliding pivot point lever mechanism, and the third acting as variable damper. A prototype was built and its performance measured with an effective stiffness changing time of 50 to 120 ms for small to large stiffness steps, nominal output velocity of 16 rad/s and a variable damper with a damping torque from 0 to 3 Nm. Its effective stiffness range is 0.2 to 313 Nm/rad. This concludes that the new actuator is particularly suitable for highly dynamic tasks. At the same time, the new actuator is also very versatile, making it especially interesting for teleoperation and human-robot collaboration.

Explore related subjects

cs.ROcs.HC

Keep this discovery

BibTeXRIS

Manuel Aiple, Wouter Gregoor, Andre Schiele. 2019-06-18. A Dynamic Robotic Actuator with Variable Physical Stiffness and Damping. https://arxiv.org/abs/1906.07669

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedicated continuous action head trained via diffusion or flow matching. However, such heads rely on iterative multi-step sampling, for example 10 Euler steps in $\pi_{0.5}$. This creates an inference bottleneck that produces stop-and-go movement in the robot and slower task completion. We introduce IMLE-VLA, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). The cIMLE objective promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely. When IMLE-VLA is applied to $\pi_{0.5}$, it increases inference frequency 3.67x (55 Hz vs. 15 Hz), enabling up to 11x higher action throughput. On the 40-task LIBERO benchmark, IMLE-VLA achieves the highest average success rate (98.0%) among all baselines while leading in inference frequency. Under the test-time perturbations of LIBERO-plus, IMLE-VLA retains $\pi_{0.5}$'s robustness while other baselines degrade sharply, confirming that the cIMLE head preserves generalization. Real-world experiments on a Franka Emika Panda across four tasks demonstrate smoother motion (2.2x to 3.0x lower jerk) and faster task completion, with IMLE-VLA outperforming $\pi_{0.5}$ on every task and reducing average VLA inference time per episode by 3.9x to 6.6x. Videos and code are available at https://kianhk6.github.io/IMLE-VLA/

cs.RO↗
arXiv2026

ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations

Imitation learning has achieved impressive results in robotic manipulation, yet most existing approaches assume clean backgrounds and lack explicit mechanisms for obstacle-aware motion generation. Extending such policies to cluttered, real-world scenes with unstructured obstacles remains a key generalization challenge. We present ObstaDiff, a decomposed diffusion-policy framework with a lightweight obstacle-aware visual encoder. ObstaDiff extracts a structured target-obstacle-background representation, enabling the downstream alignment policy to generate end-effector trajectories toward a target-centered bottleneck pose while reasoning about surrounding obstacles. We evaluate ObstaDiff on 61 real-robot greenhouse trials per method (366 executions in total). ObstaDiff achieves 75.41% average task success and 8.20% average obstacle collision rate, outperforming representative imitation-learning baselines and improving generalization in cluttered agricultural scenes.

cs.RO↗
arXiv2026

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verification offers a way to directly address this gap. On a simulated highway and an arterial road we trained two small end-to-end steering networks each in CARLA, one on clear conditions alone and one on clear, fog, night and low sun. All four models were driven against a 2.19 ft lane-departure budget. Without driving again, we used bound propagation, a formal method that reads the trained weights, to compute how far steering can drift at every disturbance strength between two captured images. One calculation covers more than a campaign could drive: on the arterial it spans 133 poses, where ten intensities each would be 10^133 combinations, in minutes on one GPU. Not only did formal verification find conditions that broke the clear-trained policy without simulation testing, it provided some preliminary evidence for potential failures between the test cases. Our overall conclusion is that formal verification is a viable complement to simulation, and could be adopted as a part of verification and validation for automated driving.

cs.RO↗