SearcharxivSearch

arXiv subjects

Armin Maleki

Publications and source records attributed to Armin Maleki.

3 recordsLinked to original sources

HeteroPROMPT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework

Collaborative Perception (CP) improves autonomous systems' awareness of their surroundings by sharing sensor data, intermediate features, and detection results. In real-world deployments, however, collaborating vehicles often use heterogeneous sensors, perception models, datasets, and training domains, creating feature-space shifts that degrade downstream fusion and detection. Existing approaches typically retrain fusion and detection components or introduce modality-specific feature interpreters. These methods scale poorly to newly joining agents and often require access to proprietary metadata, raising privacy concerns. We propose HeteroPROMPT, a real-time and privacy-preserving framework for heterogeneous collaborative perception. HeteroPROMPT rapidly aligns each heterogeneous agent's features with an ego-centric unified feature space through modular prompts and lightweight learning-based tuning, while keeping agent encoders and the collaborative fusion and detection stacks frozen. Its visual prompt-based training and inference modulate Bird's Eye View (BEV) features across channels and spatial locations with low computational overhead. For metadata-free deployment, an autoencoder learns a compact unified representation and extracts modality cues from shared features, enabling real-time modality classification and routing to the appropriate HeteroPROMPT modules without exposing proprietary agent information. Experiments on the OPV2V-H and V2XSet datasets show that HeteroPROMPT improves Average Precision over state-of-the-art heterogeneous CP methods while using orders of magnitude fewer trainable parameters. This offers a scalable and practical CP solution. The proposed modality classifier also predicts the joining agent's modality from compact features with greater than 99.99 percent accuracy during deployment. Code will be available at https://github.com/arminmaleki007/HeteroPROMPT.

cs.CV

Faster-HEAL: An Efficient and Privacy-Preserving Collaborative Perception Framework for Heterogeneous Autonomous Vehicles

Collaborative perception (CP) is a promising paradigm for improving situational awareness in autonomous vehicles by overcoming the limitations of single-agent perception. However, most existing approaches assume homogeneous agents, which restricts their applicability in real-world scenarios where vehicles use diverse sensors and perception models. This heterogeneity introduces a feature domain gap that degrades detection performance. Prior works address this issue by retraining entire models/major components, or using feature interpreters for each new agent type, which is computationally expensive, compromises privacy, and may reduce single-agent accuracy. We propose Faster-HEAL, a lightweight and privacy-preserving CP framework that fine-tunes a low-rank visual prompt to align heterogeneous features with a unified feature space while leveraging pyramid fusion for robust feature aggregation. This approach reduces the trainable parameters by 94%, enabling efficient adaptation to new agents without retraining large models. Experiments on the OPV2V-H dataset show that Faster-HEAL improves detection performance by 2% over state-of-the-art methods with significantly lower computational overhead, offering a practical solution for scalable heterogeneous CP.

cs.CV

Activity-induced asymmetric dispersion in confined channels with constriction

Microorganisms, such as E.Coli, are known to display upstream behavior and respond rheotactically to shear flows. In particular, E.Coli suspensions have been shown to display strong sensitivity to spatial constrictions, leading to an anomalous densification past the constriction for incoming fluid velocities comparable to the microoganism's self propulsion speed. We introduce a Brownian dynamics model for ellipsoidal self-propelling particles in a confined channel subject to a constriction. The model allows to identify the relevant parameters that characterize the relevant dynamical regimes of the accumulation of the active particles at the constriction, and clarify the mechanisms underlying the experimental observations. We find that particles are trapped in butterfly-like attractors in front of the constriction, which is the origin of the symmetry breaking in the emerging density profiles of active particles passing the constriction. In addition, the probability of trapping and thus the strength of asymmetry is affected by size of the particles and geometry of the channel, as well as the ratio of fluid velocity to propulsion speed.

cond-mat.soft