arXiv subjects

Mohammad Zamani

Publications and source records attributed to Mohammad Zamani.

15 recordsLinked to original sources

arXiv2026

Vision-Language Models for Egocentric Video: From Hand-Object Interaction to Embodied AI

Egocentric video captures activities from the wearer's perspective, providing a direct view of human attention, hand--object interaction, and goal-directed behavior. This perspective is increasingly important for wearable intelligence, assistive systems, human--robot interaction, and embodied AI, yet it introduces challenges including ego-motion, occlusion, small active objects, viewpoint-dependent appearance, and long-range temporal dependencies. Vision--language models (VLMs) offer a promising foundation for addressing these challenges by linking visual observations with semantic knowledge and natural-language supervision. This survey presents a critical review of VLMs for egocentric video understanding, tracing the progression from conventional recognition architectures to multimodal foundation models and embodied systems. We organize the literature around tasks, datasets, hand--object interaction understanding, temporal reasoning, frame and clip selection, multimodal representation learning, prompting, semantic alignment, and model adaptation. Particular attention is given to graph-based and object-centric reasoning as mechanisms for modeling relations among hands, objects, actions, and scene context over time. We further examine how first-person perception and multimodal foundation models support wearable assistance, robot skill learning, human-to-robot transfer, and embodied decision making. Across the reviewed literature, a consistent limitation emerges: current models recognize visible objects more reliably than evolving interactions, actions, and user intent, especially over long activities. We therefore identify temporally grounded reasoning, interaction-aware supervision, efficient long-video processing, multimodal fusion, graph-enhanced representations, cross-domain generalization, privacy, and trustworthy evaluation as key priorities for deployable embodied intelligence.

cs.CV↗

arXiv2026

Interface-Driven Growth Mode Control of 2D GaSe on 3D GaAs Substrates with Distinct Crystallographic Orientations

Previous studies of the growth of two-dimensional (2D) gallium selenide (GaSe) by molecular beam epitaxy (MBE) on a gallium arsenide (GaAs) three-dimensional (3D) substrate have reported significant differences in growth morphology, polytype, and the nature of the interface. The results differ, ranging from GaSe 2D film growth at tilted 2D planes to observed spiral structures, thereby calling for a deeper understanding of the impact of the substrate interface on the growth of GaSe films. In this paper, we conduct a comprehensive reexamination of the growth mechanism of GaSe on GaAs substrates with (211)B and (001)B orientations, investigating the nature of the 2D/3D interface and the resulting morphology of the 2D GaSe films. We do this by investigating different methods of preparation of the GaAs substrate surface before the growth of GaSe by MBE, the importance of which has not been considered before. Our results resolve the mechanistic origin of tilted versus non-tilted 2D growth and establish a general interface-driven orientation selection rule linking substrate symmetry and dangling-bond coordination to layered heteroepitaxy. This framework provides a scalable interface-engineering pathway for deterministic control of layered chalcogenide heterostructures and enables wafer-scale integration with established semiconductor device platforms.

cond-mat.mtrl-sci↗

arXiv2023

Learning Safety Filters for Unknown Discrete-Time Linear Systems

A learning-based safety filter is developed for discrete-time linear time-invariant systems with unknown models subject to Gaussian noises with unknown covariance. Safety is characterized using polytopic constraints on the states and control inputs. The empirically learned model and process noise covariance with their confidence bounds are used to construct a robust optimization problem for minimally modifying nominal control actions to ensure safety with high probability. The optimization problem relies on tightening the original safety constraints. The magnitude of the tightening is larger at the beginning since there is little information to construct reliable models, but shrinks with time as more data becomes available.

cs.LG↗

arXiv2023

Collaborative Bearing Estimation Using Set Membership Methods

We consider the problem of collaborative bearing estimation using a method with historic roots in set theoretic estimation techniques. We refer to this method as the Convex Combination Ellipsoid (CCE) method and show that it provides a less conservative covariance estimate than the well known Covariance Intersection (CI) method. The CCE method does not introduce additional uncertainty that was not already present in the prior estimates. Using our proposed approach for collaborative bearing estimation, the nonlinearity of the bearing measurement is captured as an uncertainty ellipsoid thereby avoiding the need for linearization or approximation via sampling procedures. Simulations are undertaken to evaluate the relative performance of the collaborative bearing estimation solution using the proposed (CCE) and typical (CI) methods.

cs.IT↗

arXiv2022

A Logistic Regression Approach to Field Estimation Using Binary Measurements

In this letter, we consider the problem of field estimation using binary measurements. Previous work has formulated the problem as a parameter estimation problem, with the parameter estimation carried out in an online manner using sequential Monte Carlo techniques. In the current work, we consider an alternative approach to the parameter estimation based on online logistic regression. The developed algorithm is less computationally intensive than the sequential Monte Carlo approach, while having more reliable estimation performance.

stat.ME↗

arXiv2022

On modularity in reactive control architectures, with an application to formal verification

Modularity is a central principle throughout the design process for cyber-physical systems. Modularity reduces complexity and increases reuse of behavior. In this paper we pose and answer the following question: how can we identify independent `modules' within the structure of reactive control architectures? To this end, we propose a graph-structured control architecture we call a decision structure, and show how it generalises some reactive control architectures which are popular in Artificial Intelligence (AI) and robotics, specifically Teleo-Reactive programs (TRs), Decision Trees (DTs), Behavior Trees (BTs) and Generalised Behavior Trees ($k$-BTs). Inspired by the definition of a module in graph theory, we define modules in decision structures and show how each decision structure possesses a canonical decomposition into its modules. We can naturally characterise each of the BTs, $k$-BTs, DTs and TRs by properties of their module decomposition. This allows us to recognise which decision structures are equivalent to each of these architectures in quadratic time. Our proposed concept of modules extends to formal verification, under any verification scheme capable of verifying a decision structure. Namely, we prove that a modification to a module within a decision structure has no greater flow-on effects than a modification to an individual action within that structure. This enables verification on modules to be done locally and hierarchically, where structures can be verified and then repeatedly locally modified, with modules replaced by modules while preserving correctness. To illustrate the findings, we present an example of a solar-powered drone controlled by a decision structure. We use a Linear Temporal Logic-based verification scheme to verify the correctness of this structure, and then show how one can modify modules while preserving its correctness.

cs.AI↗

arXiv2021

A principled analysis of Behavior Trees and their generalisations

As complex autonomous robotic systems become more widespread, the need for transparent and reusable Artificial Intelligence (AI) designs becomes more apparent. In this paper we analyse how the principles behind Behavior Trees (BTs), an increasingly popular tree-structured control architecture, are applicable to these goals. Using structured programming as a guide, we analyse the BT principles of reactiveness and modularity in a formal framework of action selection. Proceeding from these principles, we review a number of challenging use cases of BTs in the literature, and show that reasoning via these principles leads to compatible solutions. Extending these arguments, we introduce a new class of control architectures we call generalised BTs or $k$-BTs and show how they can extend the applicability of BTs to some of the aforementioned challenging BT use cases while preserving the BT principles.

cs.AI↗

arXiv2021

Safe Learning of Uncertain Environments

In many learning based control methodologies, learning the unknown dynamic model precedes the control phase, while the aim is to control the system such that it remains in some safe region of the state space. In this work, our aim is to guarantee safety while learning and control proceed simultaneously. Specifically, we consider the problem of safe learning in nonlinear control-affine systems subject to unknown additive uncertainty. We first model the uncertainty as a Gaussian noise and use state measurements to learn its mean and covariance. We provide rigorous time-varying bounds on the mean and covariance of the uncertainty and employ them to modify the control input via an optimization program with potentially time-varying safety constraints. We show that with an arbitrarily large probability we can guarantee that the state will remain in the safe set, while learning and control are carried out simultaneously, provided that a feasible solution exists for the optimization problem. We provide a secondary formulation of this optimization that is computationally more efficient. This is based on tightening the safety constraints to counter the uncertainty about the learned mean and covariance. The magnitude of the tightening can be decreased as our confidence in the learned mean and covariance increases (i.e., as we gather more measurements about the environment). Extensions of the method are provided for non-Gaussian process noise with unknown mean and covariance as well as Gaussian uncertainties with state-dependent mean and covariance to accommodate more general environments.

cs.LG↗

arXiv2021

An expressiveness hierarchy of Behavior Trees and related architectures

In this paper we provide a formal framework for comparing the expressive power of Behavior Trees (BTs) to other action selection architectures. Taking inspiration from the analogous comparisons of structural programming methodologies, we formalise the concept of `expressiveness'. This leads us to an expressiveness hierarchy of control architectures, which includes BTs, Decision Trees (DTs), Teleo-reactive Programs (TRs) and Finite State Machines (FSMs). By distinguishing between BTs with auxiliary variables and those without, we demonstrate the existence of a trade-off in BT design between readability and expressiveness. We discuss what this means for BTs in practice.

cs.AI↗

arXiv2021

Inertial Collaborative Localisation for Autonomous Vehicles using a Minimum Energy Filter

Collaborative Localisation has been studied extensively in recent years as a way to improve pose estimation of unmanned aerial vehicles in challenging environments. However little attention has been paid toward advancing the underlying filter design beyond standard Extended Kalman Filter-based approaches. In this paper, we detail a discrete-time collaborative localisation filter using the deterministic minimum-energy framework. The filter incorporates measurements from an inertial measurement unit and models the effects of sensor bias and gravitational acceleration. We present a simulation based on real-world vehicle trajectories and IMU data that demonstrates how collaborative localisation can improve performance over single-vehicle methods.

cs.RO↗

arXiv2020

A Minimum Energy Filter for Localisation of an Unmanned Aerial Vehicle

Accurate localisation of unmanned aerial vehicles is vital for the next generation of automation tasks. This paper proposes a minimum energy filter for velocity-aided pose estimation on the extended special Euclidean group. The approach taken exploits the Lie-group symmetry of the problem to combine Inertial Measurement Unit (IMU) sensor output with landmark measurements into a robust and high performance state estimate. We propose an asynchronous discrete-time implementation to fuse high bandwidth IMU with low bandwidth discrete-time landmark measurements typical of real-world scenarios. The filter's performance is demonstrated by simulation.

eess.SY↗

arXiv2020

A Minimum Energy Filter for Distributed Multirobot Localisation

We present a new approach to the cooperative localisation problem by applying the theory of minimum energy filtering. We consider the problem of estimating the pose of a group of mobile robots in an environment where robots can perceive fixed landmarks and neighbouring robots as well as share information with others over a communication channel. Whereas the vast majority of the existing literature applies some variant of a Kalman Filter, we derive a set of filter equations for the global state estimate based on the principle of minimum energy filtering. We show how the filter equations can be decoupled and the calculations distributed among the robots in the network without requiring a central processing node. Finally, we provide a demonstration of the filter's performance in simulation.

eess.SY↗

arXiv2015

Back to the Past: Source Identification in Diffusion Networks from Partially Observed Cascades

When a piece of malicious information becomes rampant in an information diffusion network, can we identify the source node that originally introduced the piece into the network and infer the time when it initiated this? Being able to do so is critical for curtailing the spread of malicious information, and reducing the potential losses incurred. This is a very challenging problem since typically only incomplete traces are observed and we need to unroll the incomplete traces into the past in order to pinpoint the source. In this paper, we tackle this problem by developing a two-stage framework, which first learns a continuous-time diffusion network model based on historical diffusion traces and then identifies the source of an incomplete diffusion trace by maximizing the likelihood of the trace under the learned model. Experiments on both large synthetic and real-world data show that our framework can effectively go back to the past, and pinpoint the source node and its initiation time significantly more accurately than previous state-of-the-arts.

cs.SI↗

arXiv2014

Minimum-Energy Distributed Consensus of Uncertain Agents

This paper presents a consensus algorithm for a multi-agent system where each agent has access to its imperfect own state and neighboring state measurements. The measurements are subject to deterministic disturbances and the proposed algorithm provides a minimum-energy estimate of the measured states which is instrumental in achieving consensus by the nodes. It is shown that the proposed consensus algorithm converges exponentially in the absence of disturbances, and its performance under bounded continuous disturbances is investigated as well. The convergence performance of the proposed method is further studied using simulations where we show that consensus is achieved despite using large measurement errors.

eess.SY↗

arXiv2014

Minimum-Energy Distributed Filtering

The paper addresses the problem of distributed filtering with guaranteed convergence properties using minimum-energy filtering and $H_\infty$ filtering methodologies. A linear state space plant model is considered observed by a network of communicating sensors, in which individual sensor measurements may lead to an unobservable filtering problem. However, each filter locally shares estimates, that are subject to disturbances, with its respective neighboring filters to produce an estimate of the plant state. The minimum-energy strategy of the proposed local filter leads to a locally optimal time-varying filter gain facilitating the transient and the asymptotic convergence of the estimation error, with guaranteed $H_\infty$ performance. The filters are implementable using only the local measurements and information from the neighboring filters subject to disturbances. A key idea of the proposed algorithm is to locally approximate the neighboring estimates, that are not directly accessible, considering them as disturbance contaminated versions of the plant state. The proposed algorithm imposes minimal communication load on the network and is scalable to larger sensor networks.

eess.SY↗