We propose a diffusion approximation method to the continuous-state Markov Decision Processes (MDPs) that can be utilized to address autonomous navigation and control in unstructured off-road environments. In contrast to most decision-theoretic planning frameworks that assume fully known state transition models, we design a method that eliminates such a strong assumption that is often extremely difficult to engineer in reality. We first take the second-order Taylor expansion of the value function. The Bellman optimality equation is then approximated by a partial differential equation, which only relies on the first and second moments of the transition model. By combining the kernel representation of the value function, we then design an efficient policy iteration algorithm whose policy evaluation step can be represented as a linear system of equations characterized by a finite set of supporting states. We first validate the proposed method through extensive simulations in $2D$ obstacle avoidance and $2.5D$ terrain navigation problems. The results show that the proposed approach leads to a much superior performance over several baselines. We then develop a system that integrates our decision-making framework with onboard perception and conduct real-world experiments in both cluttered indoor and unstructured outdoor environments. The results from the physical systems further demonstrate the applicability of our method in challenging real-world environments.
相關內容
Tilt-series alignment is crucial to obtaining high-resolution reconstructions in cryo-electron tomography. Beam-induced local deformation of the sample is hard to estimate from the low-contrast sample alone, and often requires fiducial gold bead markers. The state-of-the-art approach for deformation estimation uses (semi-)manually labelled marker locations in projection data to fit the parameters of a polynomial deformation model. Manually-labelled marker locations are difficult to obtain when data are noisy or markers overlap in projection data. We propose an alternative mathematical approach for simultaneous marker localization and deformation estimation by extending a grid-free super-resolution algorithm first proposed in the context of single-molecule localization microscopy. Our approach does not require labelled marker locations; instead, we use an image-based loss where we compare the forward projection of markers with the observed data. We equip this marker localization scheme with an additional deformation estimation component and solve for a reduced number of deformation parameters. Using extensive numerical studies on marker-only samples, we show that our approach automatically finds markers and reliably estimates sample deformation without labelled marker data. We further demonstrate the applicability of our approach for a broad range of model mismatch scenarios, including experimental electron tomography data of gold markers on ice.
Continuous determinantal point processes (DPPs) are a class of repulsive point processes on $\mathbb{R}^d$ with many statistical applications. Although an explicit expression of their density is known, it is too complicated to be used directly for maximum likelihood estimation. In the stationary case, an approximation using Fourier series has been suggested, but it is limited to rectangular observation windows and no theoretical results support it. In this contribution, we investigate a different way to approximate the likelihood by looking at its asymptotic behaviour when the observation window grows towards $\mathbb{R}^d$. This new approximation is not limited to rectangular windows, is faster to compute than the previous one, does not require any tuning parameter, and some theoretical justifications are provided. It moreover provides an explicit formula for estimating the asymptotic variance of the associated estimator. The performances are assessed in a simulation study on standard parametric models on $\mathbb{R}^d$ and compare favourably to common alternative estimation methods for continuous DPPs.
In this paper, we place deep Q-learning into a control-oriented perspective and study its learning dynamics with well-established techniques from robust control. We formulate an uncertain linear time-invariant model by means of the neural tangent kernel to describe learning. We show the instability of learning and analyze the agent's behavior in frequency-domain. Then, we ensure convergence via robust controllers acting as dynamical rewards in the loss function. We synthesize three controllers: state-feedback gain scheduling $\mathcal{H}_2$, dynamic $\mathcal{H}_\infty$, and constant gain $\mathcal{H}_\infty$ controllers. Setting up the learning agent with a control-oriented tuning methodology is more transparent and has well-established literature compared to the heuristics in reinforcement learning. In addition, our approach does not use a target network and randomized replay memory. The role of the target network is overtaken by the control input, which also exploits the temporal dependency of samples (opposed to a randomized memory buffer). Numerical simulations in different OpenAI Gym environments suggest that the $\mathcal{H}_\infty$ controlled learning performs slightly better than Double deep Q-learning.
This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties and proposes a controller that combines Adaptive Control (AC) in the inner loop and a Reinforcement Learning (RL) based policy in the outer loop. Two classes of nonlinear dynamic systems are considered, both of which are control-affine. The first class of dynamic systems utilizes equilibrium points with expansion forms around these points and employs a Lyapunov approach. The second class of nonlinear systems uses contraction theory as the underlying framework. For both classes of systems, the AC-RL controller is shown to lead to online policies that guarantee stability, and leverage accelerated convergence properties using a high-order tuner. Additionally, for the second class of systems, the AC-RL controller is shown to lead to parameter learning with persistent excitation. Numerical validations of all algorithms are carried out using a quadrotor landing task on a moving platform and other academic examples. All results clearly point out the advantage of the proposed integrative AC-RL approach.
An informative measurement is the most efficient way to gain information about an unknown state. We give a first-principles derivation of a general-purpose dynamic programming algorithm that returns an optimal sequence of informative measurements by sequentially maximizing the entropy of possible measurement outcomes. This algorithm can be used by an autonomous agent or robot to decide where best to measure next, planning a path corresponding to an optimal sequence of informative measurements. The algorithm is applicable to states and controls that are continuous or discrete, and agent dynamics that is either stochastic or deterministic; including Markov decision processes and Gaussian processes. Recent results from approximate dynamic programming and reinforcement learning, including on-line approximations such as rollout and Monte Carlo tree search, allow the measurement task to be solved in real-time. The resulting solutions include non-myopic paths and measurement sequences that can generally outperform, sometimes substantially, commonly used greedy approaches. This is demonstrated for a global search problem, where on-line planning with an extended local search is found to reduce the number of measurements in the search by approximately half. A variant of the algorithm is derived for Gaussian processes for active sensing.
We present a framework for a controlled Markov chain where the state of the chain is only given at chosen observation times and of a cost. Optimal strategies therefore involve the choice of observation times as well as the subsequent control values. We show that the corresponding value function satisfies a dynamic programming principle, which leads to a system of quasi-variational inequalities (QVIs). Next, we give an extension where the model parameters are not known a priori but are inferred from the costly observations by Bayesian updates. We then prove a comparison principle for a larger class of QVIs, which implies uniqueness of solutions to our proposed problem. We utilise penalty methods to obtain arbitrarily accurate solutions. Finally, we perform numerical experiments on three applications which illustrate our framework.
In this paper we propose a robotic system for Irrigation Water Management (IWM) in a structured robotic greenhouse environment. A commercially available robotic manipulator is equipped with an RGB-D camera and a soil moisture sensor. The two are used to automate the procedure known as "feel and appearance method", which is a way of monitoring soil moisture to determine when to irrigate and how much water to apply. We develop a compliant force control framework that enables the robot to insert the soil moisture sensor in the sensitive plant root zone of the soil, without harming the plant. RGB-D camera is used to roughly estimate the soil surface, in order to plan the soil sampling approach. Used together with the developed adaptive force control algorithm, the camera enables the robot to sample the soil without knowing the exact soil stiffness a priori. Finally, we postulate a deep learning based approach to utilize the camera to visually assess the soil health and moisture content.
Breakthroughs in machine learning in the last decade have led to `digital intelligence', i.e. machine learning models capable of learning from vast amounts of labeled data to perform several digital tasks such as speech recognition, face recognition, machine translation and so on. The goal of this thesis is to make progress towards designing algorithms capable of `physical intelligence', i.e. building intelligent autonomous navigation agents capable of learning to perform complex navigation tasks in the physical world involving visual perception, natural language understanding, reasoning, planning, and sequential decision making. Despite several advances in classical navigation methods in the last few decades, current navigation agents struggle at long-term semantic navigation tasks. In the first part of the thesis, we discuss our work on short-term navigation using end-to-end reinforcement learning to tackle challenges such as obstacle avoidance, semantic perception, language grounding, and reasoning. In the second part, we present a new class of navigation methods based on modular learning and structured explicit map representations, which leverage the strengths of both classical and end-to-end learning methods, to tackle long-term navigation tasks. We show that these methods are able to effectively tackle challenges such as localization, mapping, long-term planning, exploration and learning semantic priors. These modular learning methods are capable of long-term spatial and semantic understanding and achieve state-of-the-art results on various navigation tasks.
We present R-LINS, a lightweight robocentric lidar-inertial state estimator, which estimates robot ego-motion using a 6-axis IMU and a 3D lidar in a tightly-coupled scheme. To achieve robustness and computational efficiency even in challenging environments, an iterated error-state Kalman filter (ESKF) is designed, which recursively corrects the state via repeatedly generating new corresponding feature pairs. Moreover, a novel robocentric formulation is adopted in which we reformulate the state estimator concerning a moving local frame, rather than a fixed global frame as in the standard world-centric lidar-inertial odometry(LIO), in order to prevent filter divergence and lower computational cost. To validate generalizability and long-time practicability, extensive experiments are performed in indoor and outdoor scenarios. The results indicate that R-LINS outperforms lidar-only and loosely-coupled algorithms, and achieve competitive performance as the state-of-the-art LIO with close to an order-of-magnitude improvement in terms of speed.
This paper presents a safety-aware learning framework that employs an adaptive model learning method together with barrier certificates for systems with possibly nonstationary agent dynamics. To extract the dynamic structure of the model, we use a sparse optimization technique, and the resulting model will be used in combination with control barrier certificates which constrain feedback controllers only when safety is about to be violated. Under some mild assumptions, solutions to the constrained feedback-controller optimization are guaranteed to be globally optimal, and the monotonic improvement of a feedback controller is thus ensured. In addition, we reformulate the (action-)value function approximation to make any kernel-based nonlinear function estimation method applicable. We then employ a state-of-the-art kernel adaptive filtering technique for the (action-)value function approximation. The resulting framework is verified experimentally on a brushbot, whose dynamics is unknown and highly complex.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191