arXiv subjects

Arvind Easwaran

Publications and source records attributed to Arvind Easwaran.

At least 37 records · Page 2Linked to original sources

arXiv2025

Improving Reinforcement Learning Sample-Efficiency using Local Approximation

In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting that are sharper than those in existing literature. The premise of our study is twofold: firstly, the further two states are from each other, transition-wise, the less relevant the value of the first state is when learning the $ε$-optimal value of the second; secondly, the amount of 'effort', sample-complexity-wise, expended in learning the $ε$-optimal value of a state is independent of the number of samples required to learn the $ε$-optimal value of a second state that is a sufficient number of transitions away from the first. Inversely, states within each other's vicinity have values that are dependent on each other and will require a similar number of samples to learn. By approximating the original MDP using smaller MDPs constructed using subsets of the original's state-space, we are able to reduce the sample-complexity by a logarithmic factor to $O(SA \log A)$ timesteps, where $S$ and $A$ are the state and action space sizes. We are able to extend these results to an infinite-horizon, model-free setting by constructing a PAC-MDP algorithm with the aforementioned sample-complexity. We conclude with showing how significant the improvement is by comparing our algorithm against prior work in an experimental setting.

cs.LG↗

arXiv2025

Energy-Efficient Real-Time Job Mapping and Resource Management in Mobile-Edge Computing

Mobile-edge computing (MEC) has emerged as a promising paradigm for enabling Internet of Things (IoT) devices to handle computation-intensive jobs. Due to the imperfect parallelization of algorithms for job processing on servers and the impact of IoT device mobility on data communication quality in wireless networks, it is crucial to jointly consider server resource allocation and IoT device mobility during job scheduling to fully benefit from MEC, which is often overlooked in existing studies. By jointly considering job scheduling, server resource allocation, and IoT device mobility, we investigate the deadline-constrained job offloading and resource management problem in MEC with both communication and computation contentions, aiming to maximize the total energy saved for IoT devices. For the offline version of the problem, where job information is known in advance, we formulate it as an Integer Linear Programming problem and propose an approximation algorithm, $\mathtt{LHJS}$, with a constant performance guarantee. For the online version, where job information is only known upon release, we propose a heuristic algorithm, $\mathtt{LBS}$, that is invoked whenever a job is released. Finally, we conduct experiments with parameters from real-world applications to evaluate their performance.

cs.DC↗

arXiv2025

Controlled Reach-avoid Set Computation for Discrete-time Polynomial Systems via Convex Optimization

This paper addresses the computation of controlled reach-avoid sets (CRASs) for discrete-time polynomial systems subject to control inputs. A CRAS is a set encompassing initial states from which there exist control inputs driving the system into a target set while avoiding unsafe sets. However, efficiently computing CRASs remains an open problem, especially for discrete-time systems. In this paper, we propose a novel framework for computing CRASs which takes advantage of a probabilistic perspective. This framework transforms the fundamentally nonlinear problem of computing CRASs into a computationally tractable convex optimization problem. By regarding control inputs as disturbances obeying certain probability distributions, a CRAS can be equivalently treated as a 0-reach-avoid set in the probabilistic sense, which consists of initial states from which the probability of eventually entering the target set while remaining within the safe set is greater than zero. Thus, we can employ the convex optimization method of computing 0-reach-avoid sets to estimate CRASs. Furthermore, inspired by the $ε$-greedy strategy widely used in reinforcement learning, we propose an approach that iteratively updates the aforementioned probability distributions imposed on control inputs to compute larger CRASs. We demonstrate the effectiveness of the proposed method on extensive examples.

eess.SY↗

arXiv2025

CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving

Lane keeping in autonomous driving systems requires scenario-specific weight tuning for different objectives. We formulate lane-keeping as a constrained reinforcement learning problem, where weight coefficients are automatically learned along with the policy, eliminating the need for scenario-specific tuning. Empirically, our approach outperforms traditional RL in efficiency and reliability. Additionally, real-world demonstrations validate its practical value for real-world autonomous driving.

cs.LG↗

arXiv2025

Local Ratio based Real-time Job Offloading and Resource Allocation in Mobile Edge Computing

Mobile Edge Computing (MEC) has emerged as a promising paradigm enabling vehicles to handle computation-intensive and time-sensitive applications for intelligent transportation. Due to the limited resources in MEC, effective resource management is crucial for improving system performance. While existing studies mostly focus on the job offloading problem and assume that job resource demands are fixed and given apriori, the joint consideration of job offloading (selecting the edge server for each job) and resource allocation (determining the bandwidth and computation resources for offloading and processing) remains underexplored. This paper addresses the joint problem for deadline-constrained jobs in MEC with both communication and computation resource constraints, aiming to maximize the total utility gained from jobs. To tackle this problem, we propose an approximation algorithm, $\mathtt{IDAssign}$, with an approximation bound of $\frac{1}{6}$, and experimentally evaluate the performance of $\mathtt{IDAssign}$ by comparing it to state-of-the-art heuristics using a real-world taxi trace and object detection applications.

cs.DC↗

arXiv2025

Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation

An issue concerning the use of deep reinforcement learning (RL) agents is whether they can be trusted to perform reliably when deployed, as training environments may not reflect real-life environments. Anticipating instances outside their training scope, learning-enabled systems are often equipped with out-of-distribution (OOD) detectors that alert when a trained system encounters a state it does not recognize or in which it exhibits uncertainty. There exists limited work conducted on the problem of OOD detection within RL, with prior studies being unable to achieve a consensus on the definition of OOD execution within the context of RL. By framing our problem using a Markov Decision Process, we assume there is a transition distribution mapping each state-action pair to another state with some probability. Based on this, we consider the following definition of OOD execution within RL: A transition is OOD if its probability during real-life deployment differs from the transition distribution encountered during training. As such, we utilize conditional variational autoencoders (CVAE) to approximate the transition dynamics of the training environment and implement a conformity-based detector using reconstruction loss that is able to guarantee OOD detection with a pre-determined confidence level. We evaluate our detector by adapting existing benchmarks and compare it with existing OOD detection models for RL.

cs.LG↗

arXiv2024

A novel load distribution strategy for aggregators using IoT-enabled mobile devices

The rapid proliferation of Internet-of-things (IoT) as well as mobile devices such as Electric Vehicles (EVs), has led to unpredictable load at the grid. The demand to supply ratio is particularly exacerbated at a few grid aggregators (charging stations) with excessive demand due to the geographic location, peak time, etc. Existing solutions on demand response cannot achieve significant improvements based only on time-shifting the loads without considering the device properties such as charging modes and movement capabilities to enable geographic migration. Additionally, the information on the spare capacity at a few aggregators can aid in re-channeling the load from other aggregators facing excess demand to allow migration of devices. In this paper, we model these flexible properties of the devices as a mixed-integer non-linear problem (MINLP) to minimize excess load and the improve the utility (benefit) across all devices. We propose an online distributed low-complexity heuristic that prioritizes devices based on demand and deadlines to minimize the cumulative loss in utility. The proposed heuristic is tested on an exhaustive set of synthetic data and compared with solutions from a solver/optimization tool for the same runtime to show the impracticality of using a solver. A real-world EV testbed data is also tested with our proposed solution and other scheduling solutions to show the practicality of generating a feasible schedule and a loss improvement of at least 57.23%.

cs.MA↗

arXiv2024

A Location Validation Technique to Mitigate GPS Spoofing Attacks in IEEE 802.11p based Fleet Operator's Network of Electric Vehicles

Most vehicular applications in electric vehicles use IEEE 802.11p protocol for vehicular communications. Vehicle rebalancing application is one such application that has been used by many car rental service providers to overcome the disparity between vehicle demand and vehicle supply at different charging stations. Vehicle rebalancing application uses the GPS location data of the vehicles periodically to determine the vehicle(s) to be moved to a different charging station for rebalancing. However, a malicious attacker residing in the network can spoof the GPS location data packets of the target vehicle(s) resulting in misinterpretation of the location of the vehicle(s). This can result in wrong rebalancing decision leading to unmet demands of the customers and under utilization of the system. To detect and prevent this attack, we propose a location tracking technique that can validate the current location of a vehicle based on its previous location and roadmaps. We used OpenStreetMap and SUMO simulator to generate the roadmap data from the roadmaps of Singapore. Extensive experiments on the generated datasets show the efficacy of our proposed technique.

cs.CR↗

arXiv2024

Vanilla Gradient Descent for Oblique Decision Trees

Decision Trees (DTs) constitute one of the major highly non-linear AI models, valued, e.g., for their efficiency on tabular data. Learning accurate DTs is, however, complicated, especially for oblique DTs, and does take a significant training time. Further, DTs suffer from overfitting, e.g., they proverbially "do not generalize" in regression tasks. Recently, some works proposed ways to make (oblique) DTs differentiable. This enables highly efficient gradient-descent algorithms to be used to learn DTs. It also enables generalizing capabilities by learning regressors at the leaves simultaneously with the decisions in the tree. Prior approaches to making DTs differentiable rely either on probabilistic approximations at the tree's internal nodes (soft DTs) or on approximations in gradient computation at the internal node (quantized gradient descent). In this work, we propose DTSemNet, a novel semantically equivalent and invertible encoding for (hard, oblique) DTs as Neural Networks (NNs), that uses standard vanilla gradient descent. Experiments across various classification and regression benchmarks show that oblique DTs learned using DTSemNet are more accurate than oblique DTs of similar size learned using state-of-the-art techniques. Further, DT training time is significantly reduced. We also experimentally demonstrate that DTSemNet can learn DT policies as efficiently as NN policies in the Reinforcement Learning (RL) setup with physical inputs (dimensions $\leq32$). The code is available at https://github.com/CPS-research-group/dtsemnet.

cs.LG↗

arXiv2024

Methods for Mitigating Uncertainty in Real-Time Operations of a Connected Microgrid

In this paper, we compare the effectiveness of a two-stage control strategy for the energy management system (EMS) of a grid-connected microgrid under uncertain solar irradiance and load demand using a real-world dataset from an island in Southeast Asia (SEA). The first stage computes a day-ahead commitment for power profile exchanged with the main grid, while the second stage focuses on real-time controls to minimize the system operating cost. Given the challenges in accurately forecasting solar irradiance for a long time horizon, scenario-based stochastic programming (SP) is considered for the first stage. For the second stage, as the most recent weather conditions can be used, several methodologies to handle the uncertainties are investigated, including: (1) the rule-based method historically deployed on EMS, (2) model predictive controller (MPC) using either an explicit forecast or scenario-based stochastic forecast, and (3) Deep Reinforcement Learning (DRL) computing its own implicit forecast through a distribution of costs. Performances of these methodologies are compared in terms of precision with a reference control assuming perfect forecast -- i.e. representing the minimal achievable operation cost in theory. Obtained results show that MPC with a stochastic forecast outperforms MPC with a simple deterministic prediction. This suggests that using an explicit forecast, even within a short time window, is challenging. Using weather conditions can, however, be more efficient, as demonstrated by DRL (with implicit forecast), outperforming MPC with stochastic forecast by 1.3\%.

eess.SY↗

arXiv2024

Cluster-based Network Time Synchronization for Resilience with Energy Efficiency

Time synchronization of devices in Internet-of-Things (IoT) networks is one of the challenging problems and a pre-requisite for the design of low-latency applications. Although many existing solutions have tried to address this problem, almost all solutions assume all the devices (nodes) in the network are faultless. Furthermore, these solutions exchange a large number of messages to achieve synchronization, leading to significant communication and energy overhead. To address these shortcomings, we propose C-sync, a clustering-based decentralized time synchronization protocol that provides resilience against several types of faults with energy-efficient communication. C-sync achieves scalability by introducing multiple reference nodes in the network that restrict the maximum number of hops any node can have to its time source. The protocol is designed with a modular structure on the Contiki platform to allow application transitions. We evaluate C-sync on a real testbed that comprises over 40 Tmote Sky hardware nodes distributed across different levels in a building and show through experiments the fault resilience, energy efficiency, and scalability of the protocol. C-sync detects and isolates faults to a cluster and recovers quickly. The evaluation makes a qualitative comparison with state-of-the-art protocols and a quantitative comparison with a class of decentralized protocols (derived from GTSP) that provide synchronization with no/limited fault-tolerance. Results also show a reduction of 56.12% and 75.75% in power consumption in the worst-case and best-case scenarios, respectively, compared to GTSP, while achieving similar accuracy.

cs.DC↗

arXiv2024

Event-Driven Real-Time Multi-Objective Charging Schedule Optimization For Electric Vehicle Fleets

The utilization of Electric Vehicles (EVs) in car rental services is gaining momentum around the world and most commercial fleets are expected to fully adopt EVs by 2030. At the moment, the baseline solution that most fleet operators use is a Business as Usual (BAU) policy of charging at the maximum power at all times when charging EVs. Unlike petrol prices that are fairly constant, electricity prices are more volatile and can vary vastly within several minutes depending on electricity supply which is influenced by intermittent energy supplies like renewable energy and increased demand due to electrification in many industrial sectors including transportation. The battery in EVs is the most critical component as it is the most expensive component to replace and the most dangerous component with fire risks. For safe operation and battery longevity it is imperative to prevent battery capacity fade whenever the EVs are under the control of the fleet operator such as during charging.Fundamentally, the fleet operator would like to service as much demand as possible to maximize the revenue generated at a particular time instance.This is achieved by minimizing the EVs time spent on charging and thereby increasing their availability for rides.The three goals of reducing charging cost, battery capacity fade and maximizing ride availability are formulated as a multi-objective optimization problem. The formulation is tested using the Gurobi solver on two cases from the real-world ACN dataset involving low and high EV charging densities over a week long period. The results of the proposed solution show 33.3% reduction in peak electricity loading period, 53.2% savings in charging cost and 16% lower battery capacity fade for the fleet operator.

eess.SY↗

arXiv2024

Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment

Out-of-distribution (OOD) detectors can act as safety monitors in embedded cyber-physical systems by identifying samples outside a machine learning model's training distribution to prevent potentially unsafe actions. However, OOD detectors are often implemented using deep neural networks, which makes it difficult to meet real-time deadlines on embedded systems with memory and power constraints. We consider the class of variational autoencoder (VAE) based OOD detectors where OOD detection is performed in latent space, and apply quantization, pruning, and knowledge distillation. These techniques have been explored for other deep models, but no work has considered their combined effect on latent space OOD detection. While these techniques increase the VAE's test loss, this does not correspond to a proportional decrease in OOD detection performance and we leverage this to develop lean OOD detectors capable of real-time inference on embedded CPUs and GPUs. We propose a design methodology that combines all three compression techniques and yields a significant decrease in memory and execution time while maintaining AUROC for a given OOD detector. We demonstrate this methodology with two existing OOD detectors on a Jetson Nano and reduce GPU and CPU inference time by 20% and 28% respectively while keeping AUROC within 5% of the baseline.

cs.LG↗

arXiv2024

Function+Data Flow: A Framework to Specify Machine Learning Pipelines for Digital Twinning

The development of digital twins (DTs) for physical systems increasingly leverages artificial intelligence (AI), particularly for combining data from different sources or for creating computationally efficient, reduced-dimension models. Indeed, even in very different application domains, twinning employs common techniques such as model order reduction and modelization with hybrid data (that is, data sourced from both physics-based models and sensors). Despite this apparent generality, current development practices are ad-hoc, making the design of AI pipelines for digital twinning complex and time-consuming. Here we propose Function+Data Flow (FDF), a domain-specific language (DSL) to describe AI pipelines within DTs. FDF aims to facilitate the design and validation of digital twins. Specifically, FDF treats functions as first-class citizens, enabling effective manipulation of models learned with AI. We illustrate the benefits of FDF on two concrete use cases from different domains: predicting the plastic strain of a structure and modeling the electromagnetic behavior of a bearing.

cs.SE↗

arXiv2024

Optimal Fixed Priority Scheduling in Multi-Stage Multi-Resource Distributed Real-Time Systems

This work studies fixed priority (FP) scheduling of real-time jobs with end-to-end deadlines in a distributed system. Specifically, given a multi-stage pipeline with multiple heterogeneous resources of the same type at each stage, the problem is to assign priorities to a set of real-time jobs with different release times to access a resource at each stage of the pipeline subject to the end-to-end deadline constraints. Note, in such a system, jobs may compete with different sets of jobs at different stages of the pipeline depending on the job-to-resource mapping. To this end, following are the two major contributions of this work. We show that an OPA-compatible schedulability test based on the delay composition algebra can be constructed, which we then use with an optimal priority assignment algorithm to compute a priority ordering. Further, we establish the versatility of pairwise priority assignment in such a multi-stage multi-resource system, compared to a total priority ordering. In particular, we show that a pairwise priority assignment may be feasible even if a priority ordering does not exist. We propose an integer linear programming formulation and a scalable heuristic to compute a pairwise priority assignment. We also show through simulation experiments that the proposed approaches can be used for the holistic scheduling of real-time jobs in edge computing systems.

cs.DC↗

arXiv2023

A Low-Cost Lane-Following Algorithm for Cyber-Physical Robots

Duckiebots are low-cost mobile robots that are widely used in the fields of research and education. Although there are existing self-driving algorithms for the Duckietown platform, they are either too complex or perform too poorly to navigate a multi-lane track. Moreover, it is essential to give memory and computational resources to a Duckiebot so it can perform additional tasks such as out-of-distribution input detection. In order to satisfy these constraints, we built a low-cost autonomous driving algorithm capable of driving on a two-lane track. The algorithm uses traditional computer vision techniques to identify the central lane on the track and obtain the relevant steering angle. The steering is then controlled by a PID controller that smoothens the movement of the Duckiebot. The performance of the algorithm was compared to that of the NeurIPS 2018 AI Driving Olympics (AIDO) finalists, and it outperformed all but one finalists. The two main contributions of our algorithm are its low computational requirements and very quick set-up, with ongoing efforts to make it more reliable.

cs.CV↗

arXiv2023

Co-Design of Out-of-Distribution Detectors for Autonomous Emergency Braking Systems

Learning enabled components (LECs), while critical for decision making in autonomous vehicles (AVs), are likely to make incorrect decisions when presented with samples outside of their training distributions. Out-of-distribution (OOD) detectors have been proposed to detect such samples, thereby acting as a safety monitor, however, both OOD detectors and LECs require heavy utilization of embedded hardware typically found in AVs. For both components, there is a tradeoff between non-functional and functional performance, and both impact a vehicle's safety. For instance, giving an OOD detector a longer response time can increase its accuracy at the expense of the LEC. We consider an LEC with binary output like an autonomous emergency braking system (AEBS) and use risk, the combination of severity and occurrence of a failure, to model the effect of both components' design parameters on each other's functional and non-functional performance, as well as their impact on system safety. We formulate a co-design methodology that uses this risk model to find the design parameters for an OOD detector and LEC that decrease risk below that of the baseline system and demonstrate it on a vision based AEBS. Using our methodology, we achieve a 42.3% risk reduction while maintaining equivalent resource utilization.

cs.LG↗

arXiv2023

PAC-Based Formal Verification for Out-of-Distribution Data Detection

Cyber-physical systems (CPS) like autonomous vehicles, that utilize learning components, are often sensitive to noise and out-of-distribution (OOD) instances encountered during runtime. As such, safety critical tasks depend upon OOD detection subsystems in order to restore the CPS to a known state or interrupt execution to prevent safety from being compromised. However, it is difficult to guarantee the performance of OOD detectors as it is difficult to characterize the OOD aspect of an instance, especially in high-dimensional unstructured data. To distinguish between OOD data and data known to the learning component through the training process, an emerging technique is to incorporate variational autoencoders (VAE) within systems and apply classification or anomaly detection techniques on their latent spaces. The rationale for doing so is the reduction of the data domain size through the encoding process, which benefits real-time systems through decreased processing requirements, facilitates feature analysis for unstructured data and allows more explainable techniques to be implemented. This study places probably approximately correct (PAC) based guarantees on OOD detection using the encoding process within VAEs to quantify image features and apply conformal constraints over them. This is used to bound the detection error on unfamiliar instances with user-defined confidence. The approach used in this study is to empirically establish these bounds by sampling the latent probability distribution and evaluating the error with respect to the constraint violations that are encountered. The guarantee is then verified using data generated from CARLA, an open-source driving simulator.

cs.AI↗