Trajectory planning is one of the indispensable and critical components in robotics autonomous systems. As an efficient indirect method to deal with nonlinear system dynamics trajectory tasks over unconstrained state control space, iterative linear quadratic regulator (iLQR) has demonstrated noteworthy outcomes. In this article, a local-learning-enabled constrained iLQR algorithm herein presented for based on hybrid dynamic optimization machine learning. Rather importantly, attains key...

In the area of autonomous driving, it typically brings great difficulty in solving motion planning problem since vehicle model is nonlinear and driving scenarios are complex. Particularly, most existing methods cannot be generalized to dynamically changing with varying surrounding vehicles. To address this problem, development here investigates framework integrated decision control. As part modules, static path determines reference candidates ahead, then optimal path-tracking controller...

The uncertainties arising from the plant model and topologies have been a major challenge in multiagent consensus control. This article presents distributed robust control method for an uncertain system with eigenvalue-bounded topologies. heterogeneity of node dynamics is described as linear common certain part. transformation adopted to decompose topologically coupled controllers. Then, matrix inequalities (LMIs) technique used numerically solve controller problem. It proved that such...

Model information can be used to predict future trajectories, so it has huge potential avoid dangerous regions when applying reinforcement learning (RL) on real-world tasks, like autonomous driving. However, existing studies mostly use model-free constrained RL, which causes inevitable constraint violations. This paper proposes a model-based feasibility enhancement technique of enhances the policy using generalized control barrier function (GCBF) defined distance boundary. By model...

The World Health Organization predicts that by 2030, depression will be the most common mental disorder, significantly affecting individuals, families, and society. Speech, as a sensitive indicator, reveals noticeable acoustic changes linked to physiological cognitive variations, making it crucial behavioral marker for detecting depression. However, existing studies often overlook separation of speaker-related emotion-related features in speech when recognizing To tackle this challenge, we...

Abstract Nitrous oxide (N 2 O) is formed during wastewater nitrogen removal processes. It a strong greenhouse gas, however, if properly captured it can also be used as renewable energy source. In this study, nosZ -deficient strain of Pseudomonas aeruginosa was constructed. During growth under denitrifying conditions, the more highly transcribing other genes from denitrification pathway ( narG , nirS and norB ) than wild-type strain. This could convert 85% NO − -N to N O when grown with...

Automated vehicle controller's design can be formulated into a general optimal control problem. Existing methods not meet the millisecond-level time requirements of onboard standard controllers, especially for nonlinear dynamics with non-affine and saturated controller. This paper presents continuous-time (CT) finite-horizon approximate dynamic programming (ADP) method, which synthesis off-line near policy analytical dynamics. Firstly, we develop variant CT Hamilton-Jacobi-Bellman (HJB)...

In this paper, we propose a new state representation method, called encoding sum and concatenation (ESC), to describe the environment observation for decision-making in autonomous driving. Unlike existing methods, ESC is applicable situation where number of surrounding vehicles variable eliminates need manually pre-designed sorting rules, leading higher ability generality. The proposed method introduces feature neural network (NN) encode real-valued each vehicle into an vector, then adds...

Receding horizon control (RHC) is a popular procedure to deal with optimal problems. Due the existence of state constraints, optimization-based RHC often suffers notorious issue infeasibility, which strongly shrinks region controllable state. This paper proposes generalized barrier function (CBF) enlarge feasible constrained only one-step constraint on prediction horizon. design can reduce steps by penalizing tendency move towards boundary. Additionally, CBF able handle high-order equality...

The Hamilton-Jacobi-Bellman (HJB) equation serves as the necessary and sufficient condition for optimal solution to continuous-time (CT) control problem (OCP). Compared with infinite-horizon HJB equation, solving of finite-horizon (FH) has been a long-standing challenge, because partial time derivative value function is involved an additional unknown term. To address this problem, study first-time bridges link between terminal-time utility function, thus it facilitates use policy iteration...

This paper proposes an offline control algorithm, called Recurrent Model Predictive Control (RMPC), to solve large-scale nonlinear finite-horizon optimal problems. It can be regarded as explicit solver of traditional (MPC) algorithms, which adaptively select appropriate model prediction horizon according current computing resources, so improve the policy performance. Our algorithm employs a recurrent function approximate policy, maps system states and reference values directly inputs. The...

摘要: 在极限轮胎-路面条件下,智能汽车的横向操纵性能急剧恶化,增加了自动驾驶系统的控制难度。现有研究主要聚焦智能汽车轨迹跟踪的性能,但是难以解决低附着路面、紧急避障等极限工况下的智能汽车轨迹跟踪时的安全性和稳定性。利用模型预测控制方法实现了智能汽车的轨迹跟踪,同时保证智能汽车行驶稳定性和安全性,仿真试验同样表明该控制器具有较好的鲁棒性。结合二次型代价函数和安全约束构建了轨迹跟踪的开环最优预测控制问题,通过约束车辆的前后轮侧偏角,保持极限工况下智能汽车的行驶稳定性。研究方法与结果可为智能汽车设计提供参考。

Hamilton-Jacobi-Bellman (HJB) equation is the sufficient and necessary condition for continuous-time optimal control problem (OCP). Different from HJB in infinite horizon, finite-horizon contains a time-dependent value function, whose partial derivative with respect to time an intractable unknown term. My study has found that exactly equals terminal-time utility function by analyzing initial-time equivalency between fixed horizon OCP terminal OCP. We also provide another proof, which uses...

Receding horizon control (RHC) is a popular procedure to deal with optimal problems. Due the existence of state constraints, optimization-based RHC often suffers notorious issue infeasibility, which strongly shrinks region controllable state. This paper proposes generalized barrier function (CBF) enlarge feasible constrained only one-step constraint on prediction horizon. design can reduce steps by penalizing tendency move towards boundary. Additionally, CBF able handle high-order equality...

The design of an automated vehicle controller can be generally formulated into optimal control problem. This paper proposes a continuous-time finite-horizon approximate dynamicprogramming (ADP) method, which synthesis off-line near-optimal policy with analytical dynamics. Lying on the general Policy Iteration framework, it employs value andpolicy neural networks to mappings from thesystem states function and inputs, respectively. proposed method converge solutionof Hamilton-Jacobi-Bellman...

This paper proposes an off-line algorithm, called Recurrent Model Predictive Control (RMPC), to solve general nonlinear finite-horizon optimal control problems. Unlike traditional (MPC) algorithms, it can make full use of the current computing resources and adaptively select longest model prediction horizon. Our algorithm employs a recurrent function approximate policy, which maps system states reference values directly inputs. The number steps is equal cycles learned policy function. With...