No abstract

Extreme learning machine (ELM), characterized by its fast learning efficiency and great generalization ability, has been applied to various object recognition tasks. When extended to the stacked autoencoder network, which is a typical symmetrical representation learning model architecture, ELM manages to realize hierarchical feature extraction and classification, which is what deep neural networks usually do, but with much less training time. Nevertheless, the input weights and biases of the hidden nodes in ELM are generated according to a random distribution and may lead to the occurrence of non-optimal and redundant parameters that deteriorate discriminative features, which will have a bad influence on the final classification effect. In this paper, a novel sparse autoencoder derived from ELM and differential evolution is proposed and integrated into a hierarchical hybrid autoencoder network to accomplish the end-to-end learning with raw visible light camera sensor images and applied to several typical object recognition problems. Experimental results show that the proposed method is able to obtain competitive or better performance than current relevant methods with acceptable or less time consumption.

Autonomous decision making and motion planning in complex dynamic traffic environments, such as left-turn without traffic signals and multi-lane merging from sideways , are still challenging tasks for intelligent vehicles. It is difficult to generate optimized behavior decisions while considering the motion capabilities and dynamic properties of intelligent vehicles. Aiming at the above problems, this paper proposes a hierarchical reinforcement learning approach for autonomous decision making and motion planning in complex dynamic traffic scenarios. The proposed approach consists of two layers. At the higher layer, a kernel-based least-squares policy iteration algorithm with uneven sampling and pooling strategy (USP-KLSPI) is presented for solving the decision-making problems. The motion capabilities of the ego vehicle and the surrounding vehicles are evaluated with a high-fidelity dynamic model in the decisionmaking layer. By doing so, the consistency between the decisions generated at the higher layer and the operations in the lower planning layer can be well guaranteed. The lower layer addresses the motionplanning problem in the lateral direction using a dual heuristic programming (DHP) algorithm learned in a batch-mode manner, while the velocity profile in the longitudinal direction is inherited from the higher layer. Extensive simulations are conducted in complex traffic conditions including left-turn without traffic signals and multi-lane merging from sideways scenarios. The results demonstrate the effectiveness and efficiency of the proposed approach in realizing optimized decision making and motion planning in complex environments. INDEX TERMS Autonomous driving, hierarchical reinforcement learning, complex dynamic traffics, decision making, motion planning.

Autonomous driving promises to be the main trend in the future intelligent transportation systems due to its potentiality for energy saving, and traffic and safety improvements. However, traditional autonomous vehicles’ behavioral decisions face consistency issues between behavioral decision and trajectory planning and shows a strong dependence on the human experience. In this paper, we present a planning-feature-based deep behavior decision method (PFBD) for autonomous driving in complex, dynamic traffic. We used a deep reinforcement learning (DRL) learning framework with the twin delayed deep deterministic policy gradient algorithm (TD3) to exploit the optimal policy. We took into account the features of topological routes in the decision making of autonomous vehicles, through which consistency between decision making and path planning layers can be guaranteed. Specifically, the features of a route extracted from path planning space are shared as the input states for the behavioral decision. The actor-network learns a near-optimal policy from the feasible and safe candidate emulated routes. Simulation tests on three typical scenarios have been performed to demonstrate the performance of the learning policy, including the comparison with a traditional rule-based expert algorithm and the comparison with the policy considering partial information of a contour. The results show that the proposed approach can achieve better decisions. Real-time test on an HQ3 (HongQi the third ) autonomous vehicle also validated the effectiveness of PFBD.

In the real-time decision-making and local planning process of autonomous vehicles in dynamic environments, the autonomous driving system may fail to find a reasonable policy or even gets trapped in some situation due to the complexity of global tasks and the incompatibility between upper level maneuver decisions with the lower level trajectory planning. To solve this problem, this paper presents a synchronous maneuver searching and trajectory planning (SMSTP) algorithm based on the topological concept of homotopy. Firstly, a set of alternative maneuvers with boundary limits are enumerated on a multilane road. Instead of sampling numerous paths in the whole spatio-temporal space, we, for the first time, propose using Trajectory Profiles (TPs) to quickly construct the topological maneuvers represented by different routes, and put forward a corridor generation algorithm based on graph-search. The bounded corridor further constrains the maneuver's space in the spatial space. A step-wise heuristic optimization algorithm is then proposed to synchronously generate a feasible trajectory for each maneuver. To achieve real-time performance, we initialize the states to be optimized with the boundary constraints of maneuvers, and we set some heuristic states as terminal targets in the quadratic cost function. The solution of a feasible trajectory is always guaranteed only if a specific maneuver is given. The simulation and realistic driving-test experiments verified that the proposed SMSTP algorithm has a short computation time which is less than 37ms, and the experimental results showed the validity and effectiveness of the SMSTP algorithm.