arXiv subjects

Vikas Dhiman

Publications and source records attributed to Vikas Dhiman.

At least 19 recordsLinked to original sources

arXiv2026

Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks

Kolmogorov-Arnold Networks (KANs) with spline activations have recently shown promise for interpretable function approximation. Distance-Aware Error for Kolmogorov Networks (DAREK) introduces a computationally efficient bottom-up approach to uncertainty quantification by equipping KANs with distance-aware error bounds; yet, in high-dimensional settings, the theoretical guarantees can be weakened by the emergence of fictitious knots. Inspired by the Kolmogorov-Arnold representation theorem, DAREK adopts a componentwise formulation in which each input dimension is treated separately; as a result, induced knot locations may appear in the combined input space without corresponding to actual training data. These fictitious knots mislead the DAREK uncertainty estimator into reporting low uncertainty far from any real observation, violating the distance-awareness guarantee. We identify this failure mode precisely, characterize its geometric structure, and propose a drainage uncertainty mechanism that restores distance-awareness by constructing a monotonically decreasing uncertainty path from any fictitious knot region toward the nearest real knot. The proposed drainage method provides a practical heuristic correction that mitigates the fictitious-knot failure mode while restoring theoretical distance-awareness in high-dimensional settings. Experiments on a 2D synthetic benchmark and a 100-dimensional face dataset show that drainage raises sampled distance-awareness (SDA) from 85% to 98-99%, matching Gaussian processes at lower computational cost.

cs.LG↗

arXiv2026

Worst-Case Distance-Aware Error Bounds for Neural Networks

Safety-critical applications of machine learning require uncertainty estimates that support reliable worst-case analysis. Neural networks (NNs) provide expressive function approximation, while Gaussian processes (GPs) offer principled probabilistic uncertainty, but both face limitations in this setting: most modern neural architectures lack tractable worst-case error bounds, and Gaussian processes become computationally expensive at scale. For uncertainty to be interpretable, a central requirement is distance-awareness: that is, uncertainty increases with the distance between a test input and the nearest relevant training data. We present a general framework for worst-case distance-aware error bounds for NNs that combine dense layers with spline-based components. Our approach establishes error bounds that are both distance-aware, reflecting proximity of a test point to its nearest training data, and worst-case, providing deterministic guarantees under known Lipschitz constraints rather than probabilistic assumptions. Our algorithm, K-DAREK (Distance-Aware Error for Kurkova-Kolmogorov Networks), provides efficient and interpretable uncertainty quantification for NNs. K-DAREK is about four times faster and ten times more computationally efficient than an ensemble of KANs, 8.6 times more scalable than GP, eliminates up to 8.2% error-bound violation rate observed in DAREK, and reduces the average collision rate from 1.8% to 1.1% in the multi-agent safe control experiment. On high-dimensional real-world regression tasks (e.g., Real Estate Valuation), K-DAREK preserves distance-aware error bounds and achieves zero coverage violations, addressing the overgeneralization and inducing-point-coverage limitations exhibited by SNGP and DUE, respectively.

cs.LG↗

arXiv2026

Capture, Shield, or Neutralize: Engagement-Aware Pursuit-Evasion

This paper introduces a hierarchical control architecture for multi-agent adversarial environments, decoupling strategic task planning from rigorous safety assurance. The system formulates pursuit-evasion as a zero-sum receding-horizon game, solved via an iterative minimax \acl{mpc} scheme. This allows pursuers to anticipate and block evader trajectories using transverse velocity penalties rather than relying on reactive heuristic formations. To guarantee collision-free operation without compromising the convexity of the \acl{mpc}, a discrete-time \acl{cbf} operates as an inner-loop safety filter. Through simulated experiments, we demonstrate the framework's adaptability. By simply altering the weights of the shared zero-sum payoff and \acl{cbf} constraints, the swarm can fluidly switch from aggressive pursuit-evasion tactics to strict perimeter defense and area denial, demonstrating robust performance across varying rules of engagement without structural changes to the control logic. The source code is available: https://github.com/ananya-ac/pursuit-evasion-mpc-cbf.

eess.SY↗

arXiv2026

Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty

We develop a new class of distance-aware error bounds that tightly characterize the approximation error of spline neural networks. Our bottom-up approach analyzes the error bound of each neuron (a spline) and then extends it to the full network. We begin with error bounds for Newton's polynomial, generalize them to arbitrary splines under higher-order Lipschitz continuity, and extend the result to function compositions, the core of deep networks such as Kolmogorov-Arnold networks. By analyzing error propagation through composed spline layers, we obtain error bounds for the entire network. These bounds are deterministic, do not rely on sampling or probabilistic assumptions, and hold under mild regularity conditions. We evaluate our method on object shape estimation from sparse laser scans and safe navigation in unstructured environments. Our method is faster than the Gaussian process and Monte Carlo approaches, and our bounds reliably enclose the true error. We also develop a metric for the distance-awareness of an uncertainty estimator and show that distance-aware uncertainty for Kolmogorov networks (DAREK) is distance-aware in more regions than the baselines.

eess.SP↗

arXiv2025

Weather-Aware Object Detection Transformer for Domain Adaptation

RT-DETRs have shown strong performance across various computer vision tasks but are known to degrade under challenging weather conditions such as fog. In this work, we investigate three novel approaches to enhance RT-DETR robustness in foggy environments: (1) Domain Adaptation via Perceptual Loss, which distills domain-invariant features from a teacher network to a student using perceptual supervision; (2) Weather Adaptive Attention, which augments the attention mechanism with fog-sensitive scaling by introducing an auxiliary foggy image stream; and (3) Weather Fusion Encoder, which integrates a dual-stream encoder architecture that fuses clear and foggy image features via multi-head self and cross-attention. Despite the architectural innovations, none of the proposed methods consistently outperform the baseline RT-DETR. We analyze the limitations and potential causes, offering insights for future research in weather-aware object detection.

cs.CV↗

arXiv2024

FogGuard: guarding YOLO against fog using perceptual loss

In this paper, we present FogGuard, a novel fog-aware object detection network designed to address the challenges posed by foggy weather conditions. Autonomous driving systems heavily rely on accurate object detection algorithms, but adverse weather conditions can significantly impact the reliability of deep neural networks (DNNs). Existing approaches include image enhancement techniques like IA-YOLO and domain adaptation methods. While image enhancement aims to generate clear images from foggy ones, which is more challenging than object detection in foggy images, domain adaptation does not require labeled data in the target domain. Our approach involves fine-tuning on a specific dataset to address these challenges efficiently. FogGuard compensates for foggy conditions in the scene, ensuring robust performance by incorporating YOLOv3 as the baseline algorithm and introducing a unique Teacher-Student Perceptual loss for accurate object detection in foggy environments. Through comprehensive evaluations on standard datasets like PASCAL VOC and RTTS, our network significantly improves performance, achieving a 69.43\% mAP compared to YOLOv3's 57.78\% on the RTTS dataset. Additionally, we demonstrate that while our training method slightly increases time complexity, it doesn't add overhead during inference compared to the regular YOLO network.

cs.CV↗

arXiv2024

Omobot: a low-cost mobile robot for autonomous search and fall detection

Detecting falls among the elderly and alerting their community responders can save countless lives. We design and develop a low-cost mobile robot that periodically searches the house for the person being monitored and sends an email to a set of designated responders if a fall is detected. In this project, we make three novel design decisions and contributions. First, our custom-designed low-cost robot has advanced features like omnidirectional wheels, the ability to run deep learning models, and autonomous wireless charging. Second, we improve the accuracy of fall detection for the YOLOv8-Pose-nano object detection network by 6% and YOLOv8-Pose-large by 12%. We do so by transforming the images captured from the robot viewpoint (camera height 0.15m from the ground) to a typical human viewpoint (1.5m above the ground) using a principally computed Homography matrix. This improves network accuracy because the training dataset MS-COCO on which YOLOv8-Pose is trained is captured from a human-height viewpoint. Lastly, we improve the robot controller by learning a model that predicts the robot velocity from the input signal to the motor controller.

cs.RO↗

arXiv2024

DADEE: Well-calibrated uncertainty quantification in neural networks for barriers-based robot safety

Uncertainty-aware controllers that guarantee safety are critical for safety critical applications. Among such controllers, Control Barrier Functions (CBFs) based approaches are popular because they are fast, yet safe. However, most such works depend on Gaussian Processes (GPs) or MC-Dropout for learning and uncertainty estimation, and both approaches come with drawbacks: GPs are non-parametric methods that are slow, while MC-Dropout does not capture aleatoric uncertainty. On the other hand, modern Bayesian learning algorithms have shown promise in uncertainty quantification. The application of modern Bayesian learning methods to CBF-based controllers has not yet been studied. We aim to fill this gap by surveying uncertainty quantification algorithms and evaluating them on CBF-based safe controllers. We find that model variance-based algorithms (for example, Deep ensembles, MC-dropout, etc.) and direct estimation-based algorithms (such as DEUP) have complementary strengths. Algorithms in the former category can only estimate uncertainty accurately out-of-domain, while those in the latter category can only do so in-domain. We combine the two approaches to obtain more accurate uncertainty estimates both in- and out-of-domain. As measured by the failure rate of a simulated robot, this results in a safer CBF-based robot controller.

cs.RO↗

arXiv2024

Cross-view geo-localization: a survey

Cross-view geo-localization has garnered notable attention in the realm of computer vision, spurred by the widespread availability of copious geotagged datasets and the advancements in machine learning techniques. This paper provides a thorough survey of cutting-edge methodologies, techniques, and associated challenges that are integral to this domain, with a focus on feature-based and deep learning strategies. Feature-based methods capitalize on unique features to establish correspondences across disparate viewpoints, whereas deep learning-based methodologies deploy convolutional neural networks to embed view-invariant attributes. This work also delineates the multifaceted challenges encountered in cross-view geo-localization, such as variations in viewpoints and illumination, the occurrence of occlusions, and it elucidates innovative solutions that have been formulated to tackle these issues. Furthermore, we delineate benchmark datasets and relevant evaluation metrics, and also perform a comparative analysis of state-of-the-art techniques. Finally, we conclude the paper with a discussion on prospective avenues for future research and the burgeoning applications of cross-view geo-localization in an intricately interconnected global landscape.

cs.CV↗

arXiv2022

Safe Control Synthesis with Uncertain Dynamics and Constraints

This paper considers safe control synthesis for dynamical systems with either probabilistic or worst-case uncertainty in both the dynamics model and the safety constraints. We formulate novel probabilistic and robust (worst-case) control Lyapunov function (CLF) and control barrier function (CBF) constraints that take into account the effect of uncertainty in either case. We show that either the probabilistic or the robust (worst-case) formulation leads to a second-order cone program (SOCP), which enables efficient safe and stable control synthesis. We evaluate our approach in PyBullet simulations of an autonomous robot navigating in unknown environments and compare the performance with a baseline CLF-CBF quadratic programming approach.

cs.RO↗

arXiv2021

Control Barriers in Bayesian Learning of System Dynamics

This paper focuses on learning a model of system dynamics online while satisfying safety constraints. Our objective is to avoid offline system identification or hand-specified models and allow a system to safely and autonomously estimate and adapt its own model during operation. Given streaming observations of the system state, we use Bayesian learning to obtain a distribution over the system dynamics. Specifically, we propose a new matrix variate Gaussian process (MVGP) regression approach with an efficient covariance factorization to learn the drift and input gain terms of a nonlinear control-affine system. The MVGP distribution is then used to optimize the system behavior and ensure safety with high probability, by specifying control Lyapunov function (CLF) and control barrier function (CBF) chance constraints. We show that a safe control policy can be synthesized for systems with arbitrary relative degree and probabilistic CLF-CBF constraints by solving a second order cone program (SOCP). Finally, we extend our design to a self-triggering formulation, adaptively determining the time at which a new control input needs to be applied in order to guarantee safety.

eess.SY↗

arXiv2021

OrcVIO: Object residual constrained Visual-Inertial Odometry

Introducing object-level semantic information into simultaneous localization and mapping (SLAM) system is critical. It not only improves the performance but also enables tasks specified in terms of meaningful objects. This work presents OrcVIO, for visual-inertial odometry tightly coupled with tracking and optimization over structured object models. OrcVIO differentiates through semantic feature and bounding-box reprojection errors to perform batch optimization over the pose and shape of objects. The estimated object states aid in real-time incremental optimization over the IMU-camera states. The ability of OrcVIO for accurate trajectory estimation and large-scale object-level mapping is evaluated using real data.

cs.RO↗

arXiv2021

Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning

This paper focuses on inverse reinforcement learning for autonomous navigation using distance and semantic category observations. The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory. We develop a map encoder, that infers semantic category probabilities from the observation sequence, and a cost encoder, defined as a deep neural network over the semantic features. Since the expert cost is not directly observable, the model parameters can only be optimized by differentiating the error between demonstrated controls and a control policy computed from the cost estimate. We propose a new model of expert behavior that enables error minimization using a closed-form subgradient computed only over a subset of promising states via a motion planning algorithm. Our approach allows generalizing the learned behavior to new environments with new spatial configurations of the semantic categories. We analyze the different components of our model in a minigrid environment. We also demonstrate that our approach learns to follow traffic rules in the autonomous driving CARLA simulator by relying on semantic observations of buildings, sidewalks, and road lanes.

cs.LG↗

arXiv2020

Learning Navigation Costs from Demonstration with Semantic Observations

This paper focuses on inverse reinforcement learning (IRL) for autonomous robot navigation using semantic observations. The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory. We develop a map encoder, which infers semantic class probabilities from the observation sequence, and a cost encoder, defined as deep neural network over the semantic features. Since the expert cost is not directly observable, the representation parameters can only be optimized by differentiating the error between demonstrated controls and a control policy computed from the cost estimate. The error is optimized using a closed-form subgradient computed only over a subset of promising states via a motion planning algorithm. We show that our approach learns to follow traffic rules in the autonomous driving CARLA simulator by relying on semantic observations of cars, sidewalks and road lanes.

cs.LG↗

arXiv2020

Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics

This paper focuses on learning a model of system dynamics online while satisfying safety constraints.Our motivation is to avoid offline system identification or hand-specified dynamics models and allowa system to safely and autonomously estimate and adapt its own model during online operation.Given streaming observations of the system state, we use Bayesian learning to obtain a distributionover the system dynamics. In turn, the distribution is used to optimize the system behavior andensure safety with high probability, by specifying a chance constraint over a control barrier function.

cs.RO↗

arXiv2020

Learning Navigation Costs from Demonstration in Partially Observable Environments

This paper focuses on inverse reinforcement learning (IRL) to enable safe and efficient autonomous navigation in unknown partially observable environments. The objective is to infer a cost function that explains expert-demonstrated navigation behavior while relying only on the observations and state-control trajectory used by the expert. We develop a cost function representation composed of two parts: a probabilistic occupancy encoder, with recurrent dependence on the observation sequence, and a cost encoder, defined over the occupancy features. The representation parameters are optimized by differentiating the error between demonstrated controls and a control policy computed from the cost encoder. Such differentiation is typically computed by dynamic programming through the value function over the whole state space. We observe that this is inefficient in large partially observable environments because most states are unexplored. Instead, we rely on a closed-form subgradient of the cost-to-go obtained only over a subset of promising states via an efficient motion-planning algorithm such as A* or RRT. Our experiments show that our model exceeds the accuracy of baseline IRL algorithms in robot navigation tasks, while substantially improving the efficiency of training and test-time inference.

cs.LG↗

arXiv2019

Learning from Interventions using Hierarchical Policies for Safe Learning

Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert's reaction time and only learns short-term behavior. We address these limitations by 1) interpolating the expert's interventions back in time, and 2) by splitting the policy into two hierarchical levels, one that generates sub-goals for the future and another that generates actions to reach those desired sub-goals. This sub-goal prediction forces the algorithm to learn long-term behavior while also being robust to the expert's reaction time. Our experiments show that LfI using sub-goals in a hierarchical policy framework trains faster and achieves better asymptotic performance than typical LfD.

cs.RO↗

arXiv2019

A Critical Investigation of Deep Reinforcement Learning for Navigation

The navigation problem is classically approached in two steps: an exploration step, where map-information about the environment is gathered; and an exploitation step, where this information is used to navigate efficiently. Deep reinforcement learning (DRL) algorithms, alternatively, approach the problem of navigation in an end-to-end fashion. Inspired by the classical approach, we ask whether DRL algorithms are able to inherently explore, gather and exploit map-information over the course of navigation. We build upon Mirowski et al. [2017] work and introduce a systematic suite of experiments that vary three parameters: the agent's starting location, the agent's target location, and the maze structure. We choose evaluation metrics that explicitly measure the algorithm's ability to gather and exploit map-information. Our experiments show that when trained and tested on the same maps, the algorithm successfully gathers and exploits map-information. However, when trained and tested on different sets of maps, the algorithm fails to transfer the ability to gather and exploit map-information to unseen maps. Furthermore, we find that when the goal location is randomized and the map is kept static, the algorithm is able to gather and exploit map-information but the exploitation is far from optimal. We open-source our experimental suite in the hopes that it serves as a framework for the comparison of future algorithms and leads to the discovery of robust alternatives to classical navigation methods.

cs.RO↗