We present a novel reinforcement learning (RL) based task allocation and decentralized navigation algorithm for mobile robots in warehouse environments. Our approach is designed for scenarios in which multiple robots are used to perform various pick up and delivery tasks. We consider the problem of joint decentralized task allocation and navigation and present a two level approach to solve it. At the higher level, we solve the task allocation by formulating it in terms of Markov Decision Processes and choosing the appropriate rewards to minimize the Total Travel Delay (TTD). At the lower level, we use a decentralized navigation scheme based on ORCA that enables each robot to perform these tasks in an independent manner, and avoid collisions with other robots and dynamic obstacles. We combine these lower and upper levels by defining rewards for the higher level as the feedback from the lower level navigation algorithm. We perform extensive evaluation in complex warehouse layouts with large number of agents and highlight the benefits over state-of-the-art algorithms based on myopic pickup distance minimization and regret-based task selection. We observe improvement up to 14% in terms of task completion time and up-to 40% improvement in terms of computing collision-free trajectories for the robots.

In this paper, we present a Bayesian method for statistical model checking (SMC) of probabilistic hyperproperties specified in the logic HyperPCTL* on discrete-time Markov chains (DTMCs). While SMC of HyperPCTL* using sequential probability ratio test (SPRT) has been explored before, we develop an alternative SMC algorithm based on Bayesian hypothesis testing. In comparison to PCTL*, verifying HyperPCTL* formulae is complex owing to their simultaneous interpretation on multiple paths of the DTMC. In addition, extending the bottom-up model-checking algorithm of the non-probabilistic setting is not straight forward due to the fact that SMC does not return exact answers to the satisfiability problems of subformulae, instead, it only returns correct answers with high-confidence. We propose a recursive algorithm for SMC of HyperPCTL* based on a modified Bayes' test that factors in the uncertainty in the recursive satisfiability results. We have implemented our algorithm in a Python toolbox, HyProVer, and compared our approach with the SPRT based SMC. Our experimental evaluation demonstrates that our Bayesian SMC algorithm performs better both in terms of the verification time and the number of samples required to deduce satisfiability of a given HyperPCTL* formula.

Researchers from DeepMind, the UK's juggernaut AI lab, have forsaken the noble games of chess and Go for a more plebeian delight: football. The Google sister company yesterday published a research paper and accompanying blog post detailing its new neural probabilistic motor primitives (NPMP) -- a method by which artificial intelligence agents can learn to operate physical bodies. An NPMP is a general-purpose motor control module that translates short-horizon motor intentions to low-level control signals, and it's trained offline or via RL by imitating motion capture (MoCap) data, recorded with trackers on humans or animals performing motions of interest. And be the first in line for ticket offers, event news, and more! Up front: Essentially, the DeepMind team created an AI system that can learn how to do things inside of a physics simulator by watching videos of other agents performing those tasks. And, of course, if you've got a giant physics engine and an endless supply of curious robots, the only rational thing to do is to teach it how to dribble and shoot: We optimized teams of agents to play simulated football via reinforcement learning, constraining the solution space to that of plausible movements learned using human motion capture data.

Training multiple agents to perform safe and cooperative control in the complex scenarios of autonomous driving has been a challenge. For a small fleet of cars moving together, this paper proposes Lepus, a new approach to training multiple agents. Lepus adopts a pure cooperative manner for training multiple agents, featured with the shared parameters of policy networks and the shared reward function of multiple agents. In particular, Lepus pre-trains the policy networks via an adversarial process, improving its collaborative decision-making capability and further the stability of car driving. Moreover, for alleviating the problem of sparse rewards, Lepus learns an approximate reward function from expert trajectories by combining a random network and a distillation network. We conduct extensive experiments on the MADRaS simulation platform. The experimental results show that multiple agents trained by Lepus can avoid collisions as many as possible while driving simultaneously and outperform the other four methods, that is, DDPG-FDE, PSDDPG, MADDPG, and MAGAIL(DDPG) in terms of stability.

The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJACI-ECAI 2022) took place from 23-29 July, in Vienna. The title of her talk was "Engineering sociality and collaboration in AI systems". Robots are widely used in industrial settings, but what happens when they enter our everyday world, and, specifically, social situations? Ana believes that social robots, chatbots and social agents have the potential to change the way we interact with technology. She envisages a hybrid society where humans and AI systems work in tandem.

Although the consensus problem has been extensively investigated, the ties among agents are assumed to be characterized by scalar-weighted networks, which fail in characterizing interdependencies among higher-dimensional states of neighboring agents. Recently, a broader category of networks termed matrix-weighted networks has been introduced which is an immediate generalization of scalar-weighted networks Sun and Yu [27], Pan et al. [23, 20], Trinh et al. [28], Pan et al. [21, 22], Wang et al. [30], Pan et al. [19]. In fact, matrix-weighted networks naturally become relevant in scenarios such as graph effective resistance based distributed control and estimation Barooah and Hespanha [2], logical inter-dependency of multiple topics in opinion evolution Friedkin et al. [8], bearing-based formation control Zhao and Zelazo [37], array of coupled LC oscillators Tuna [29] as well as consensus and synchronization on matrix-weighted networks Trinh et al. [28], Pan et al. [20]. As opposed to scalar-weighted networks, connectivity alone does not translate to achieving consensus for matrixweighted networks. To this end, properties of weight matrices play an important role in characterizing consensus. For instance, positive definiteness and positive semi-definiteness of weight matrices have been employed to provide consensus conditions in Trinh et al. [28]; negative definiteness and negative semi-definiteness of weight matrices

Deception is prevalent in human social settings. However, studies into the effect of deception on reinforcement learning algorithms have been limited to simplistic settings, restricting their applicability to complex real-world problems. This paper addresses this by introducing a new mixed competitive-cooperative multi-agent reinforcement learning (MARL) environment inspired by popular role-based deception games such as Werewolf, Avalon, and Among Us. The environment's unique challenge lies in the necessity to cooperate with other agents despite not knowing if they are friend or foe. Furthermore, we introduce a model of deception, which we call Bayesian belief manipulation (BBM) and demonstrate its effectiveness at deceiving other agents in this environment while also increasing the deceiving agent's performance.

In recent years the research in the field of autonomous vehicles has gained considerable momentum, and the idea of relieving the burden of driving from humans starts to lose its futuristic science fiction aura. Some people believe that autonomous traffic is "our last hope" of relief from the frequent road-jams, we now witness in even mid-size urban areas. We envision roads of the future with fully autonomous vehicles, that not only track the lane, keep safe distance and assist the driver, but essentially liberate humans from driving related activities altogether.

Researchers from DeepMind, the UK's juggernaut AI lab, have forsaken the noble games of chess and Go for a more plebeian delight: football. The Google sister company yesterday published a research paper and accompanying blog post detailing its new neural probabilistic motor primitives (NPMP) -- a method by which artificial intelligence agents can learn to operate physical bodies. An NPMP is a general-purpose motor control module that translates short-horizon motor intentions to low-level control signals, and it's trained offline or via RL by imitating motion capture (MoCap) data, recorded with trackers on humans or animals performing motions of interest. Up front: Essentially, the DeepMind team created an AI system that can learn how to do things inside of a physics simulator by watching videos of other agents performing those tasks. And, of course, if you've got a giant physics engine and an endless supply of curious robots, the only rational thing to do is to teach it how to dribble and shoot: We optimized teams of agents to play simulated football via reinforcement learning, constraining the solution space to that of plausible movements learned using human motion capture data. Background: In order to train AI to operate and control robots in the world, researchers have to prepare the machines for reality.

The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJACI-ECAI 2022) took place from 23-29 July, in Vienna. In this post, we continue our round-up of the invited talks, summarising the presentation by Ana Paiva, University of Lisbon and INESC-ID. The title of her talk was "Engineering sociality and collaboration in AI systems". Robots are widely used in industrial settings, but what happens when they enter our everyday world, and, specifically, social situations? Ana believes that social robots, chatbots and social agents have the potential to change the way we interact with technology.