arXiv subjects

Panagiotis Tsiotras

Publications and source records attributed to Panagiotis Tsiotras.

At least 73 records · Page 4Linked to original sources

arXiv2024

Discrete-Time Maximum Likelihood Neural Distribution Steering

This paper studies the problem of steering the distribution of a discrete-time dynamical system from an initial distribution to a target distribution in finite time. The formulation is fully nonlinear, allowing the use of general control policies, parametrized by neural networks. Although similar solutions have been explored in the continuous-time context, extending these techniques to systems with discrete dynamics is not trivial. The proposed algorithm results in a regularized maximum likelihood optimization problem, which is solved using machine learning techniques. After presenting the algorithm, we provide several numerical examples that illustrate the capabilities of the proposed method. We start from a simple problem that admits a solution through semidefinite programming, serving as a benchmark for the proposed approach. Then, we employ the framework in more general problems that cannot be solved using existing techniques, such as problems with non-Gaussian boundary distributions and non-linear dynamics.

eess.SY↗

arXiv2024

Chance-Constrained Information-Theoretic Stochastic Model Predictive Control with Safety Shielding

This paper introduces a novel nonlinear stochastic model predictive control path integral (MPPI) method, which considers chance constraints on system states. The proposed belief-space stochastic MPPI (BSS-MPPI) applies Monte-Carlo sampling to evaluate state distributions resulting from underlying systematic disturbances, and utilizes a Control Barrier Function (CBF) inspired heuristic in belief space to fulfill the specified chance constraints. Compared to several previous stochastic predictive control methods, our approach applies to general nonlinear dynamics without requiring the computationally expensive system linearization step. Moreover, the BSS-MPPI controller can solve optimization problems without limiting the form of the objective function and chance constraints. By multi-threading the sampling process using a GPU, we can achieve fast real-time planning for time- and safety-critical tasks such as autonomous racing. Our results on a realistic race-car simulation study show significant reductions in constraint violation compared to some of the prior MPPI approaches, while being comparable in computation times.

cs.RO↗

arXiv2024

Neural Visibility Field for Uncertainty-Driven Active Mapping

This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views lead to inherently unreliable color predictions by NeRF at this region, resulting in increased uncertainty in the synthesized views. To address this, we propose to use Bayesian Networks to composite position-based field uncertainty into ray-based uncertainty in camera observations. Consequently, NVF naturally assigns higher uncertainty to unobserved regions, aiding robots to select the most informative next viewpoints. Extensive evaluations show that NVF excels not only in uncertainty quantification but also in scene reconstruction for active mapping, outperforming existing methods.

cs.CV↗

arXiv2024

Data-Driven Robust Covariance Control for Uncertain Linear Systems

The theory of covariance control and covariance steering (CS) deals with controlling the dispersion of trajectories of a dynamical system, under the implicit assumption that accurate prior knowledge of the system being controlled is available. In this work, we consider the problem of steering the distribution of a discrete-time, linear system subject to exogenous disturbances under an unknown dynamics model. Leveraging concepts from behavioral systems theory, the trajectories of this unknown, noisy system may be (approximately) represented using system data collected through experimentation. Using this fact, we formulate a direct data-driven covariance control problem using input-state data. We then propose a maximum likelihood uncertainty quantification method to estimate and bound the noise realizations in the data collection process. Lastly, we utilize robust convex optimization techniques to solve the resulting norm-bounded uncertain convex program. We illustrate the proposed end-to-end data-driven CS algorithm on a double integrator example and showcase the efficacy and accuracy of the proposed method compared to that of model-based methods

eess.SY↗

arXiv2024

Computationally Efficient Chance Constrained Covariance Control with Output Feedback

This paper studies the problem of developing computationally efficient solutions for steering the distribution of the state of a stochastic, linear dynamical system between two boundary Gaussian distributions in the presence of chance-constraints on the state and control input. It is assumed that the state is only partially available through a measurement model corrupted with noise. The filtered state is reconstructed with a Kalman filter, the chance constraints are reformulated as difference of convex (DC) constraints, and the resulting covariance control problem is reformulated as a DC program, which is solved using successive convexification. The efficiency of the proposed method is illustrated on a double integrator example with varying time horizons, and is compared to other state-of-the-art chance constrained covariance control methods.

eess.SY↗

arXiv2024

Adaptive Dual Covariance Steering with Active Parameter Estimation

This work examines the optimal covariance steering problem for systems subject to unknown parameters that enter multiplicatively with the state and control, in addition to additive disturbances. In contrast to existing works, the unknown parameters are modeled as random variables and are estimated online. This work proposes the utilization of recursive least squares estimation for efficient parameter identification. A dual control problem is formulated in which the effect of the planned control policy on the parameter estimates is modeled and optimized for. The parameter estimates are then used to modify the pre-computed control policy online in an adaptive control fashion. Finally, the proposed approach is demonstrated in a vehicle control example with closed-loop parameter identification.

eess.SY↗

arXiv2024

Distributionally Robust Density Control with Wasserstein Ambiguity Sets

Precise control under uncertainty requires a good understanding and characterization of the noise affecting the system. This paper studies the problem of steering state distributions of dynamical systems subject to partially known uncertainties. We model the distributional uncertainty of the noise process in terms of Wasserstein ambiguity sets, which, based on recent results, have been shown to be an effective means of capturing and propagating uncertainty through stochastic LTI systems. To this end, we propagate the distributional uncertainty of the state through the dynamical system, and, using an affine feedback control law, we steer the ambiguity set of the state to a prescribed, terminal ambiguity set. We also enforce distributionally robust CVaR constraints for the transient motion of the state so as to reside within a prescribed constraint space. The resulting optimization problem is formulated as a semi-definite program, which can be solved efficiently using standard off-the-shelf solvers. We illustrate the proposed distributionally-robust framework on a quadrotor landing problem subject to wind turbulence.

math.OC↗

arXiv2024

Zero-Sum Games between Large-Population Teams: Reachability-based Analysis under Mean-Field Sharing

This work studies the behaviors of two large-population teams competing in a discrete environment. The team-level interactions are modeled as a zero-sum game while the agent dynamics within each team is formulated as a collaborative mean-field team problem. Drawing inspiration from the mean-field literature, we first approximate the large-population team game with its infinite-population limit. Subsequently, we construct a fictitious centralized system and transform the infinite-population game to an equivalent zero-sum game between two coordinators. We study the optimal coordination strategies for each team via a novel reachability analysis and later translate them back to decentralized strategies that the original agents deploy. We prove that the strategies are $ε$-optimal for the original finite-population team game, and we further show that the suboptimality diminishes when team size approaches infinity. The theoretical guarantees are verified by numerical examples.

eess.SY↗

arXiv2024

Desensitization and Deception in Differential Games with Asymmetric Information

Desensitization addresses safe optimal planning under parametric uncertainties by providing sensitivity function-based risk estimates. This paper expands upon the existing work on desensitization in optimal control to address safe planning for a class of two-player differential games. In the proposed game, parametric uncertainties correspond to variations of the model parameters for each player about their nominal values. The two players in the proposed formulation are assumed to have perfect information about these nominal parameter values. However, it is assumed that only one of the players has complete knowledge of the actual parameter value, resulting in information asymmetry in the proposed game. This lack of knowledge regarding the parameter variations is expected to result in state constraint violations for the player with an information disadvantage. In this regard, a desensitized feedback strategy that provides safe trajectories is proposed for the player with incomplete information. The proposed feedback strategy is evaluated for instances involving a single pursuer and a single evader with an uncertain moving obstacle, where the pursuer is assumed to only know the nominal value of the obstacle's speed. At the same time, the evader knows the obstacle's true speed, and also the fact that the pursuer knows only the nominal value of the obstacle's speed. Subsequently, deceptive strategies are proposed for the evader, who has an information advantage, and these strategies are assessed against the pursuer's desensitized strategy.

eess.SY↗

arXiv2023

Keypoint-based Stereophotoclinometry for Characterizing and Navigating Small Bodies: A Factor Graph Approach

This paper proposes the incorporation of techniques from stereophotoclinometry (SPC) into a keypoint-based structure-from-motion (SfM) system to estimate the surface normal and albedo at detected landmarks to improve autonomous surface and shape characterization of small celestial bodies from in-situ imagery. In contrast to the current state-of-the-practice method for small body shape reconstruction, i.e., SPC, which relies on human-in-the-loop verification and high-fidelity a priori information to achieve accurate results, we forego the expensive maplet estimation step and instead leverage dense keypoint measurements and correspondences from an autonomous keypoint detection and matching method based on deep learning to provide the necessary photogrammetric constraints. Moreover, we develop a factor graph-based approach allowing for simultaneous optimization of the spacecraft's pose, landmark positions, Sun-relative direction, and surface normals and albedos via fusion of Sun sensor measurements and image keypoint measurements. The proposed framework is validated on real imagery of the Cornelia crater on Asteroid 4 Vesta, along with pose estimation and mapping comparison against an SPC reconstruction, where we demonstrate precise alignment to the SPC solution without relying on any a priori camera pose and topography information or humans-in-the-loop

cs.CV↗

arXiv2023

Beyond One Model Fits All: Ensemble Deep Learning for Autonomous Vehicles

Deep learning has revolutionized autonomous driving by enabling vehicles to perceive and interpret their surroundings with remarkable accuracy. This progress is attributed to various deep learning models, including Mediated Perception, Behavior Reflex, and Direct Perception, each offering unique advantages and challenges in enhancing autonomous driving capabilities. However, there is a gap in research addressing integrating these approaches and understanding their relevance in diverse driving scenarios. This study introduces three distinct neural network models corresponding to Mediated Perception, Behavior Reflex, and Direct Perception approaches. We explore their significance across varying driving conditions, shedding light on the strengths and limitations of each approach. Our architecture fuses information from the base, future latent vector prediction, and auxiliary task networks, using global routing commands to select appropriate action sub-networks. We aim to provide insights into effectively utilizing diverse modeling strategies in autonomous driving by conducting experiments and evaluations. The results show that the ensemble model performs better than the individual approaches, suggesting that each modality contributes uniquely toward the performance of the overall model. Moreover, by exploring the significance of each modality, this study offers a roadmap for future research in autonomous driving, emphasizing the importance of leveraging multiple models to achieve robust performance.

cs.RO↗

arXiv2023

Active Learning with Dual Model Predictive Path-Integral Control for Interaction-Aware Autonomous Highway On-ramp Merging

Merging into dense highway traffic for an autonomous vehicle is a complex decision-making task, wherein the vehicle must identify a potential gap and coordinate with surrounding human drivers, each of whom may exhibit diverse driving behaviors. Many existing methods consider other drivers to be dynamic obstacles and, as a result, are incapable of capturing the full intent of the human drivers via this passive planning. In this paper, we propose a novel dual control framework based on Model Predictive Path-Integral control to generate interactive trajectories. This framework incorporates a Bayesian inference approach to actively learn the agents' parameters, i.e., other drivers' model parameters. The proposed framework employs a sampling-based approach that is suitable for real-time implementation through the utilization of GPUs. We illustrate the effectiveness of our proposed methodology through comprehensive numerical simulations conducted in both high and low-fidelity simulation scenarios focusing on autonomous on-ramp merging.

cs.RO↗

arXiv2023

Discrete-time Optimal Covariance Steering via Semidefinite Programming

This paper addresses the optimal covariance steering problem for stochastic discrete-time linear systems subject to probabilistic state and control constraints. A method is presented for efficiently attaining the exact solution of the problem based on a lossless convex relaxation of the original non-linear program using semidefinite programming. Both the constrained and the unconstrained versions of the problem with either equality or inequality terminal covariance boundary conditions are addressed. We first prove that the proposed relaxation is lossless for all of the above cases. A numerical example is then provided to illustrate the method. Finally, a comparative study is performed in systems of various sizes and steering horizons to illustrate the advantages of the proposed method in terms of computational resources compared to the state of the art.

eess.SY↗

arXiv2023

Communication-Aware Map Compression for Online Path-Planning

This paper addresses the problem of the communication of optimally compressed information for mobile robot path-planning. In this context, mobile robots compress their current local maps to assist another robot in reaching a target in an unknown environment. We propose a framework that sequentially selects the optimal compression, guided by the robot's path, by balancing the map resolution and communication cost. Our approach is tractable in close-to-real scenarios and does not necessitate prior environment knowledge. We design a novel decoder that leverages compressed information to estimate the unknown environment via convex optimization with linear constraints and an encoder that utilizes the decoder to select the optimal compression. Numerical simulations are conducted in a large close-to-real map and a maze map and compared with two alternative approaches. The results confirm the effectiveness of our framework in assisting the robot reach its target by reducing transmitted information, on average, by approximately 50% while maintaining satisfactory performance.

cs.RO↗

arXiv2023

LEA: An A Variant Algorithm with Improved Edge Efficiency for Robot Motion Planning

In this work, we introduce a new graph search algorithm, lazy edged based A* (LEA*), for robot motion planning. By using an edge queue and exploiting the idea of lazy search, LEA* is optimally vertex efficient similar to A*, and has improved edge efficiency compared to A*. LEA* is simple and easy to implement with minimum modification to A*, resulting in a very small overhead compared to previous lazy search algorithms. We also explore the effect of inflated heuristics, which results in the weighted LEA* (wLEA*). We show that the edge efficiency of wLEA* becomes close to LazySP and, thus is near-optimal. We test LEA* and wLEA* on 2D planning problems and planning of a 7-DOF manipulator. We perform a thorough comparison with previous algorithms by considering sparse, medium, and cluttered random worlds and small, medium, and large graph sizes. Our results show that LEA* and wLEA* are the fastest algorithms to find the plan compared to previous algorithms.

cs.RO↗

arXiv2023

Kinodynamic FMT* with Dimensionality Reduction Heuristics and Neural Network Controllers

This paper proposes a new sampling-based kinodynamic motion planning algorithm, called FMT*PFF, for nonlinear systems. It exploits the novel idea of dimensionality reduction using partial-final-state-free (PFF) optimal controllers.With the proposed dimensionality reduction heuristic, the search space is restricted within a subspace, thus faster convergence is achieved compared to a regular kinodynamic FMT*. The dimensionality reduction heuristic can be viewed as a sampling strategy and asymptotic optimality is preserved when combined with uniform full-state sampling. Another feature of FMT*PFF is the ability to deal with a steering function with inexact steering, which is vital when using learning-based steering functions. Learning-based methods allow us to solve the steering problem for nonlinear systems efficiently. However, learning-based methods often fail to reach the exact goal state. For nonlinear systems, we train a neural network controller using supervised learning to generate the steering commands. We show that FMT*PFF with a learning-based steering function is efficient and generates dynamically feasible motion plans. We compare our algorithm with previous algorithms and show superior performance in various simulations.

cs.RO↗

arXiv2023

KARNet: Kalman Filter Augmented Recurrent Neural Network for Learning World Models in Autonomous Driving Tasks

Autonomous driving has received a great deal of attention in the automotive industry and is often seen as the future of transportation. The development of autonomous driving technology has been greatly accelerated by the growth of end-to-end machine learning techniques that have been successfully used for perception, planning, and control tasks. An important aspect of autonomous driving planning is knowing how the environment evolves in the immediate future and taking appropriate actions. An autonomous driving system should effectively use the information collected from the various sensors to form an abstract representation of the world to maintain situational awareness. For this purpose, deep learning models can be used to learn compact latent representations from a stream of incoming data. However, most deep learning models are trained end-to-end and do not incorporate any prior knowledge (e.g., from physics) of the vehicle in the architecture. In this direction, many works have explored physics-infused neural network (PINN) architectures to infuse physics models during training. Inspired by this observation, we present a Kalman filter augmented recurrent neural network architecture to learn the latent representation of the traffic flow using front camera images only. We demonstrate the efficacy of the proposed model in both imitation and reinforcement learning settings using both simulated and real-world datasets. The results show that incorporating an explicit model of the vehicle (states estimated using Kalman filtering) in the end-to-end learning significantly increases performance.

cs.LG↗

arXiv2023

Batch Belief Trees for Motion Planning Under Uncertainty

In this work, we develop the Batch Belief Trees (BBT) algorithm for motion planning under motion and sensing uncertainties. The algorithm interleaves between batch sampling, building a graph of nominal trajectories in the state space, and searching over the graph to find belief space motion plans. By searching over the graph, BBT finds sophisticated plans that will visit (and revisit) information-rich regions to reduce uncertainty. One of the key benefits of this algorithm is the modified interplay between exploration and exploitation. Instead of an exhaustive search (exploitation) after one exploration step, the proposed algorithm uses batch samples to explore the state space and, in addition, does not require exhaustive search before the next iteration of batch sampling, which adds flexibility.The algorithm finds motion plans that converge to the optimal one as more samples are added to the graph. We test BBT in different planning environments. Our numerical investigation confirms that BBT finds non-trivial motion plans and is faster compared with previous similar methods.

cs.RO↗