This paper addresses the challenge of solving Constrained Markov Decision Processes (CMDPs) with $d > 1$ constraints when the transition dynamics are unknown, but samples can be drawn from a generative model. We propose a model-based algorithm for infinite horizon CMDPs with multiple constraints in the tabular setting, aiming to derive and prove sample complexity bounds for learning near-optimal policies. Our approach tackles both the relaxed and strict feasibility settings, where relaxed feasibility allows some constraint violations, and strict feasibility requires adherence to all constraints. The main contributions include the development of the algorithm and the derivation of sample complexity bounds for both settings. For the relaxed feasibility setting we show that our algorithm requires $\tilde{\mathcal{O}} \left( \frac{d |\mathcal{S}| |\mathcal{A}| \log(1/\delta)}{(1-\gamma)^3\epsilon^2} \right)$ samples to return $\epsilon$-optimal policy, while in the strict feasibility setting it requires $\tilde{\mathcal{O}} \left( \frac{d^3 |\mathcal{S}| |\mathcal{A}| \log(1/\delta)}{(1-\gamma)^5\epsilon^2{\zeta_{\mathbf{c}}^*}^2} \right)$ samples.

The synthesis of a smooth tracking control policy for Euler-Lagrangian (EL) systems with stringent regions of operation induced by state, input and temporal (SIT) constraints is a very challenging task. In contrast with existing methods that utilize prior knowledge of EL model parameters and uncertainty bounds, this study proposes an approximation-free adaptive barrier function-based control policy to ensure local prescribed time convergence of tracking error under state and input constraints. The proposed control policy accomplishes this by utilizing smooth time-based generator functions embedded in the filtered tracking error, which is combined with a saturation function that limits control action and confines states within the prescribed limits by enforcing the time-varying bounds on the filtered tracking error. Importantly, corresponding feasibility conditions pertaining to the minimum control authority, maximum disturbance rejection capability of the control policy, and the viable set of initial conditions are derived, illuminating the narrow operating domain of the EL systems arising from the interplay of SIT constraints. Numerical validation studies with three different robotic manipulators are employed to demonstrate the efficacy of the proposed scheme. A detailed performance comparison study with leading alternative designs is also undertaken to illustrate the superior performance of the proposed scheme.

Efficient and safe trajectory planning plays a critical role in the application of quadrotor unmanned aerial vehicles. Currently, the inherent trade-off between constraint compliance and computational efficiency enhancement in UAV trajectory optimization problems has not been sufficiently addressed. To enhance the performance of UAV trajectory optimization, we propose a spatial-temporal iterative optimization framework. Firstly, B-splines are utilized to represent UAV trajectories, with rigorous safety assurance achieved through strict enforcement of constraints on control points. Subsequently, a set of QP-LP subproblems via spatial-temporal decoupling and constraint linearization is derived. Finally, an iterative optimization strategy incorporating guidance gradients is employed to obtain high-performance UAV trajectories in different scenarios. Both simulation and real-world experimental results validate the efficiency and high-performance of the proposed optimization framework in generating safe and fast trajectories. Our source codes will be released for community reference at https://hitsz-mas.github.io/STORM

This introduces a Online advertising, a multi-billion dollar industry, relies on realtime challenging exploration-exploitation dilemma: the advertiser must auctions to connect advertisers with users. These auctions, balance exploring different bids to estimate impression values with triggered by user queries or website visits, allow advertisers to exploiting current knowledge to bid effectively. To address this, we bid for advertising slots, such as prominent placements on search propose a novel Upper Confidence Bound (UCB)-style algorithm engine results pages or in social media feeds. Advertisers aim to that carefully manages this trade-off. Via a rigorous theoretical maximize their returns, measured in conversions or other relevant analysis, we prove that our algorithm achieves ( log(|B|)) metrics, by carefully determining their bids while adhering to regret and constraint violation, where is the number of bidding budget constraints and desired return-on-spend (RoS) targets. To rounds and B is the domain of possible bids. This establishes the achieve this, a wide array of bidding strategies have been developed, first optimal regret and constraint violation bounds for bidding in leveraging techniques from optimization, online learning, and game the online setting with unknown impression values. Moreover, our theory to maximize advertiser utility [2, 7, 11, 23, 29, 30, 36, 47, 52].

-- We present the first framework demonstrating zero-shot sim-to-real transfer of visual control policies learned in a Neural Radiance Field (NeRF) environment for quadrotors to fly through racing gates. Robust transfer from simulation to real flight poses a major challenge, as standard simulators often lack sufficient visual fidelity. T o address this, we construct a photorealistic simulation environment of quadrotor racing tracks, called FalconGym, which provides effectively unlimited synthetic images for training. Within FalconGym, we develop a pipelined approach for crossing gates that combines (i) a Neural Pose Estimator (NPE) coupled with a Kalman filter to reliably infer quadrotor poses from single-frame RGB images and IMU data, and (ii) a self-attention-based multi-modal controller that adaptively integrates visual features and pose estimation. This multi-modal design compensates for perception noise and intermittent gate visibility. We train this controller purely in FalconGym with imitation learning and deploy the resulting policy to real hardware with no additional fine-tuning. Simulation experiments on three distinct tracks (circle, U-turn and figure-8) demonstrate that our controller outperforms a vision-only state-of-the-art baseline in both success rate and gate-crossing accuracy. In 30 live hardware flights spanning three tracks and 120 gates, our controller achieves a 95.8% success rate and an average error of just 10 cm when flying through 38 cm-radius gates.

Autonomous robots depend crucially on their ability to perceive and process information from dynamic, ever-changing environments. Traditional simultaneous localization and mapping (SLAM) approaches struggle to maintain consistent scene representations because of numerous moving objects, often treating dynamic elements as outliers rather than explicitly modeling them in the scene representation. In this paper, we present a novel hierarchical 3D scene graph-based SLAM framework that addresses the challenge of modeling and estimating the pose of dynamic objects and agents. We use fiducial markers to detect dynamic entities and to extract their attributes while improving keyframe selection and implementing new capabilities for dynamic entity mapping. We maintain a hierarchical representation where dynamic objects are registered in the SLAM graph and are constrained with robot keyframes and the floor level of the building with our novel entity-keyframe constraints and intra-entity constraints. By combining semantic and geometric constraints between dynamic entities and the environment, our system jointly optimizes the SLAM graph to estimate the pose of the robot and various dynamic agents and objects while maintaining an accurate map. Experimental evaluation demonstrates that our approach achieves a 27.57% reduction in pose estimation error compared to traditional methods and enables higher-level reasoning about scene dynamics.

We study the safe linear bandit problem, where an agent sequentially selects actions from a convex domain to maximize an unknown objective while ensuring unknown linear constraints are satisfied on a per-round basis. Existing approaches primarily rely on optimism-based methods with frequentist confidence bounds, often leading to computationally expensive action selection routines. We propose COnstrained Linear Thompson Sampling (COLTS), a sampling-based framework that efficiently balances regret minimization and constraint satisfaction by selecting actions on the basis of noisy perturbations of the estimates of the unknown objective vector and constraint matrix. We introduce three variants of COLTS, distinguished by the learner's available side information: - S-COLTS assumes access to a known safe action and ensures strict constraint enforcement by combining the COLTS approach with a rescaling towards the safe action. For $d$-dimensional actions, this yields $\tilde{O}(\sqrt{d^3 T})$ regret and zero constraint violations (or risk). - E-COLTS enforces constraints softly under Slater's condition, and attains regret and risk of $\tilde{O}(\sqrt{d^3 T})$ by combining COLTS with uniform exploration. - R-COLTS requires no side information, and ensures instance-independent regret and risk of $\tilde{O}(\sqrt{d^3 T})$ by leveraging repeated resampling. A key technical innovation is a coupled noise design, which maintains optimism while preserving computational efficiency, which is combined with a scaling based analysis technique to address the variation of the per-round feasible region induced by sampled constraint matrices. Our methods match the regret bounds of prior approaches, while significantly reducing computational costs compared to them, thus yielding a scalable and practical approach for constrained bandit linear optimization.

--In this paper we introduce MLINE-VINS, a novel monocular visual-inertial odometry (VIO) system that leverages line features and Manhattan Word assumption. Specifically, for line matching process, we propose a novel geometric line optical flow algorithm that efficiently tracks line features with varying lengths, whitch is do not require detections and descriptors in every frame. T o address the instability of Manhattan estimation from line features, we propose a tracking-by-detection module that consistently tracks and optimizes Manhattan framse in consecutive images. By aligning the Manhattan World with the VIO world frame, the tracking could restart using the latest pose from back-end, simplifying the coordinate transformations within the system. Furthermore, we implement a mechanism to validate Manhattan frames and a novel global structural constraints back-end optimization. Extensive experiments results on vairous datasets, including benchmark and self-collected datasets, show that the proposed approach outperforms existing methods in terms of accuracy and long-range robustness. CCURACY of pose estimation is a critical factor in various fields, such as autonomous driving, augmented reality, and robotics. Simultaneous localization and mapping (SLAM) has proven to be an effective approach to address this challenge [1], [2]. Among SLAM techniques, visual-inertial odometry (VIO) is particularly popular due to its cost-effectiveness, accuracy, and robustness. In VIO, point feature is widely used for camera pose estimation due to its simplicity and efficiency. Representative point-based VIO systems include MSCKF-VIO [3], OK-VINS [4] and VINS-MONO [5], with VINS-MONO being one of the most widely adopted algorithm. However, the performance of point-based VIO is affected by the number and spatial distribution of points and it significantly hindered in textureless environments, where the lack of texture leads to point loss. To address these limitations, line features are increasingly considered as a valuable complement to point features improving the robustness of VIO systems. Line features arecommonly found in low-texture environments, particularly in man-made environments [6].

In representation learning, uniformity refers to the uniform feature distribution in the latent space (i.e., unit hypersphere). Previous work has shown that improving uniformity contributes to the learning of under-represented classes. However, most of the previous work focused on classification; the representation space of imbalanced regression remains unexplored. Classification-based methods are not suitable for regression tasks because they cluster features into distinct groups without considering the continuous and ordered nature essential for regression. In a geometric aspect, we uniquely focus on ensuring uniformity in the latent space for imbalanced regression through two key losses: enveloping and homogeneity. The enveloping loss encourages the induced trace to uniformly occupy the surface of a hypersphere, while the homogeneity loss ensures smoothness, with representations evenly spaced at consistent intervals. Our method integrates these geometric principles into the data representations via a Surrogate-driven Representation Learning (SRL) framework. Experiments with real-world regression and operator learning tasks highlight the importance of uniformity in imbalanced regression and validate the efficacy of our geometry-based loss functions.

With the advancements in modern intelligent technologies, mobile robots equipped with manipulators are increasingly operating in unstructured environments. These robots can plan sequences of actions for long-horizon tasks based on perceived information. However, in practice, the planned actions often fail due to discrepancies between the perceptual information used for planning and the actual conditions. In this paper, we introduce the {\itshape Conditional Subtree} (CSubBT), a general self-adjusting execution framework for mobile manipulation tasks based on Behavior Trees (BTs). CSubBT decomposes symbolic action into sub-actions and uses BTs to control their execution, addressing any potential anomalies during the process. CSubBT treats common anomalies as constraint non-satisfaction problems and continuously guides the robot in performing tasks by sampling new action parameters in the constraint space when anomalies are detected. We demonstrate the robustness of our framework through extensive manipulation experiments on different platforms, both in simulation and real-world settings.