DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action Model
Pankhuri Vanjani, Zhuoyue Li, Jakub Suliga, Moritz Reuss, Gianluca Geraci, Xinkai Jiang, Rudolf Lioutikov

Preprint, 2025
Project Page  /  arXiv

Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, processing every input at one rate. This is misaligned with physical interaction, where a high-frequency modality changes at hundreds of hertz, vision evolves more slowly, and language stays constant across an episode. A synchronous VLA oversamples slow modalities, undersamples fast ones, and caps action generation at the lowest effective frequency. We hypothesize that decoupling temporal processing per modality, letting each update and retain information at its own sensor rate, yields stronger representations and more robust control. We present Decoupled Asynchronous Multimodal Vision Language Action (DAM-VLA), which maintains per-modality latent buffers refreshed at sensor rates and read continuously by the action head, integrating new high-frequency modalities through gated cross-attention that leaves the pretrained backbone intact. Across seven contact-rich real-world manipulation tasks, DAMVLA more than doubles the average success rate of the strongest synchronous baseline (95.2% vs. 40.95%) while sustaining smooth, reactive 100 Hz control

DisDP: Robust Imitation Learning via Disentangled Diffusion Policies
Pankhuri Vanjani, Paul Mattes, Xiaogang Jia, Vedant Dave, Rudolf Lioutikov

Reinforcement Learning Conference(RLC) 2025, Ext. Abstract at German Robotics Conference (GRC) 2025
OpenReviewnet

This work introduces Disentangled Diffusion Policy (DisDP), an Imitation Learning (IL) method that enhances robustness by integrating multi-view disentanglement into diffusionbased policies. For robots to be deployed on a large scale across various applications they have to be robust against different perturbations, including sensor noise, complete sensor dropout and environmental variations. Existing IL methods struggle to generalize under such conditions, as they typically assume consistent, noise-free inputs. To address this limitation, DisDP structures sensory inputs into shared and private representations, preserving task-relevant global features while retaining distinct details from individual sensors. Additionally, Disentangled Behavior Cloning (DisBC) is introduced, a disentangled Behavior Cloning (BC) policy, to demonstrate the general applicance of disentanglement for IL. This structured representation improves resilience against sensor dropouts and perturbations. Evaluations on The Colosseum and Libero benchmarks demonstrate that disentangled policies achieve better performance in general and exhibit greater robustness to any perturbations compared to their baseline policies.

Communication and networking technologies for UAVs: A survey

Journal of Network and Computer Applications, 2020
sciencedirect

This paper aims at providing insights into the latest UAV (Unmanned Aerial Vehicle) communication technologies through investigation of suitable task modules, antennas, resource handling platforms, and network architectures. Additionally, we explore techniques such as machine learning and path planning to enhance existing drone communication methods

Image processing-based intelligent robotic system for assistance of agricultural crops

International Journal of Social and Humanistic Computing, 2019
researchgate

This paper presents improved image processing algorithms for detecting leaf infections and uses k-means clustering for agricultural field classification in a heterogeneous robotic system. The approach leverages a dataset of 3,150 crop disease images across three crop types, aiming to enable early disease detection and support mixed cropping via smart farming technologies.