Autonomous navigation is challenging for mobile robots, especially in an unknown environment. Commonly, the robot requires multiple sensors to map the environment, locate itself, and make a plan to reach the target. However, reinforcement learning methods offer an alternative to map-free navigation tasks by learning the optimal actions to take. In this article, deep reinforcement learning agents are implemented using variants of the deep Q networks method, the D3QN and rainbow algorithms, for both the obstacle avoidance and the goal-oriented navigation task. The agents are trained and evaluated in a simulated environment. Furthermore, an analysis of the changes in the behaviour and performance of the agents caused by modifications in the reward function is conducted.

Autonomous Intersection Management (AIM) provides a signal-free intersection scheduling paradigm for Connected Autonomous Vehicles (CAVs). Distributed learning method has emerged as an attractive branch of AIM research. Compared with centralized AIM, distributed AIM can be deployed to CAVs at a lower cost, and compared with rule-based and optimization-based method, learning-based method can treat various complicated real-time intersection scenarios more flexibly. Deep reinforcement learning (DRL) is the mainstream approach in distributed learning to address AIM problems. However, the large-scale simultaneous interactive decision of multiple agents and the rapid changes of environment caused by interactions pose challenges for DRL, making its reward curve oscillating and hard to converge, and ultimately leading to a compromise in safety and computing efficiency. For this, we propose a non-RL learning framework, called Distributed Hierarchical Adversarial Learning (D-HAL). The framework includes an actor network that generates the actions of each CAV at each step. The immediate discriminator evaluates the interaction performance of the actor network at the current step, while the final discriminator makes the final evaluation of the overall trajectory from a series of interactions. In this framework, the long-term outcome of the behavior no longer motivates the actor network in terms of discounted rewards, but rather through a designed adversarial loss function with discriminative labels. The proposed model is evaluated at a four-way-six-lane intersection, and outperforms several state-of-the-art methods on ensuring safety and reducing travel time.

Examples of such domains are "perfect information Learning to detect, characterize and accommodate novelties is a games" such as Chess, Go, or Ms.Pac-man, where the rules challenge that agents operating in open-world domains need to of the game, the goals of the players, and the entire state of the address to be able to guarantee satisfactory task performance. Certain game are always known by all agents [10, 24, 30]. This characteristic novelties (e.g., changes in environment dynamics) can interfere simplifies the game AI behavior by limiting the number of novelties with the performance or prevent agents from accomplishing task to instances of known types (e.g., a chess move with the bishop goals altogether. In this paper, we introduce general methods and a player has not seen before), thus allowing the development of architectural mechanisms for detecting and characterizing different the game AI without needing to anticipate any unknown scenarios types of novelties, and for building an appropriate adaptive within the bounds of the system (e.g., a novel piece with novel rules model to accommodate them utilizing logical representations and being introduced).

Grasping has long been considered an important and practical task in robotic manipulation. Yet achieving robust and efficient grasps of diverse objects is challenging, since it involves gripper design, perception, control and learning, etc. Recent learning-based approaches have shown excellent performance in grasping a variety of novel objects. However, these methods either are typically limited to one single grasping mode, or else more end effectors are needed to grasp various objects. In addition, gripper design and learning methods are commonly developed separately, which may not adequately explore the ability of a multimodal gripper. In this paper, we present a deep reinforcement learning (DRL) framework to achieve multistage hybrid robotic grasping with a new soft multimodal gripper. A soft gripper with three grasping modes (i.e., enveloping, sucking, and enveloping_then_sucking) can both deal with objects of different shapes and grasp more than one object simultaneously. We propose a novel hybrid grasping method integrated with the multimodal gripper to optimize the number of grasping actions. We evaluate the DRL framework under different scenarios (i.e., with different ratios of objects of two grasp types). The proposed algorithm is shown to reduce the number of grasping actions (i.e., enlarge the grasping efficiency, with maximum values of 161% in simulations and 154% in real-world experiments) compared to single grasping modes.

Diverse and realistic traffic scenarios are crucial for evaluating the AI safety of autonomous driving systems in simulation. This work introduces a data-driven method called TrafficGen for traffic scenario generation. It learns from the fragmented human driving data collected in the real world and then can generate realistic traffic scenarios. TrafficGen is an autoregressive generative model with an encoder-decoder architecture. In each autoregressive iteration, it first encodes the current traffic context with the attention mechanism and then decodes a vehicle's initial state followed by generating its long trajectory. We evaluate the trained model in terms of vehicle placement and trajectories and show substantial improvements over baselines. TrafficGen can be also used to augment existing traffic scenarios, by adding new vehicles and extending the fragmented trajectories. We further demonstrate that importing the generated scenarios into a simulator as interactive training environments improves the performance and the safety of driving policy learned from reinforcement learning. More project resource is available at https://metadriverse.github.io/trafficgen

Smart traffic lights in intelligent transportation systems (ITSs) are envisioned to greatly increase traffic efficiency and reduce congestion. Deep reinforcement learning (DRL) is a promising approach to adaptively control traffic lights based on the real-time traffic situation in a road network. However, conventional methods may suffer from poor scalability. In this paper, we investigate deep reinforcement learning to control traffic lights, and both theoretical analysis and numerical experiments show that the intelligent behavior ``greenwave" (i.e., a vehicle will see a progressive cascade of green lights, and not have to brake at any intersection) emerges naturally a grid road network, which is proved to be the optimal policy in an avenue with multiple cross streets. As a first step, we use two DRL algorithms for the traffic light control problems in two scenarios. In a single road intersection, we verify that the deep Q-network (DQN) algorithm delivers a thresholding policy; and in a grid road network, we adopt the deep deterministic policy gradient (DDPG) algorithm. Secondly, numerical experiments show that the DQN algorithm delivers the optimal control, and the DDPG algorithm with passive observations has the capability to produce on its own a high-level intelligent behavior in a grid road network, namely, the ``greenwave" policy emerges. We also verify the ``greenwave" patterns in a $5 \times 10$ grid road network. Thirdly, the ``greenwave" patterns demonstrate that DRL algorithms produce favorable solutions since the ``greenwave" policy shown in experiment results is proved to be optimal in a specified traffic model (an avenue with multiple cross streets). The delivered policies both in a single road intersection and a grid road network demonstrate the scalability of DRL algorithms.

With the recent advancements in Vehicle-to-Vehicle communication technology, autonomous vehicles are able to connect and collaborate in platoon, minimizing accident risks, costs, and energy consumption. The significant benefits of vehicle platooning have gained increasing attention from the automation and artificial intelligence areas. However, few studies have focused on platoon with overtaking. To address this problem, the NoisyNet multi-agent deep Q-learning algorithm is developed in this paper, which the NoisyNet is employed to improve the exploration of the environment. By considering the factors of overtake, speed, collision, time headway and following vehicles, a domain-tailored reward function is proposed to accomplish safe platoon overtaking with high speed. Finally, simulation results show that the proposed method achieves successfully overtake in various traffic density situations.

In goal-conditioned offline reinforcement learning, an agent learns from previously collected data to go to an arbitrary goal. Since the offline data only contains a finite number of trajectories, a main challenge is how to generate more data. Goal-swapping generates additional data by switching trajectory goals but while doing so produces a large number of invalid trajectories. To address this issue, we propose prioritized goal-swapping experience replay (PGSER). PGSER uses a pre-trained Q function to assign higher priority weights to goal swapped transitions that allow reaching the goal. In experiments, PGSER significantly improves over baselines in a wide range of benchmark tasks, including challenging previously unsuccessful dexterous in-hand manipulation tasks.

Activation functions play a significant role in the performance of deep learning algorithms. In particular, the Swish activation function tends to outperform ReLU on deeper models, including deep reinforcement learning models, across challenging tasks. Despite this progress, ReLU is the preferred function partly because it is more efficient than Swish. Furthermore, in contrast to the fields of computer vision and natural language processing, the deep reinforcement learning and robotics domains have seen less inclination to adopt new activation functions, such as Swish, and instead continue to use more traditional functions, like ReLU. To tackle those issues, we propose Swim, a general-purpose, efficient, and high-performing alternative to Swish, and then provide an analysis of its properties as well as an explanation for its high-performance relative to Swish, in terms of both reward-achievement and efficiency. We focus on testing Swim on MuJoCo's locomotion continuous control tasks since they exhibit more complex dynamics and would therefore benefit most from a high-performing and efficient activation function. We also use the TD3 algorithm in conjunction with Swim and explain this choice in the context of the robot locomotion domain. We then conclude that Swim is a state-of-the-art activation function for continuous control locomotion tasks and recommend using it with TD3 as a working framework.

Massive random access of devices in the emerging Open Radio Access Network (O-RAN) brings great challenge to the access control and management. Exploiting the bursting nature of the access requests, sparse active user detection (SAUD) is an efficient enabler towards efficient access management, but the sparsity might be deteriorated in case of uncoordinated massive access requests. To dynamically preserve the sparsity of access requests, a reinforcement-learning (RL)-assisted scheme of closed-loop access control utilizing the access class barring technique is proposed, where the RL policy is determined through continuous interaction between the RL agent, i.e., a next generation node base (gNB), and the environment. The proposed scheme can be implemented by the near-real-time RAN intelligent controller (near-RT RIC) in O-RAN, supporting rapid switching between heterogeneous vertical applications, such as mMTC and uRLLC services. Moreover, a data-driven scheme of deep-RL-assisted SAUD is proposed to resolve highly complex environments with continuous and high-dimensional state and action spaces, where a replay buffer is applied for automatic large-scale data collection. An actor-critic framework is formulated to incorporate the strategy-learning modules into the near-RT RIC. Simulation results show that the proposed schemes can achieve superior performance in both access efficiency and user detection accuracy over the benchmark scheme for different heterogeneous services with massive access requests.