Multi-Agent Path Finding (MAPF) in crowded environments presents a challenging problem in motion planning, aiming to find collision-free paths for all agents in the system. MAPF finds a wide range of applications in various domains, including aerial swarms, autonomous warehouse robotics, and self-driving vehicles. The current approaches for MAPF can be broadly categorized into two main categories: centralized and decentralized planning. Centralized planning suffers from the curse of dimensionality and thus does not scale well in large and complex environments. On the other hand, decentralized planning enables agents to engage in real-time path planning within a partially observable environment, demonstrating implicit coordination. However, they suffer from slow convergence and performance degradation in dense environments. In this paper, we introduce CRAMP, a crowd-aware decentralized approach to address this problem by leveraging reinforcement learning guided by a boosted curriculum-based training strategy. We test CRAMP on simulated environments and demonstrate that our method outperforms the state-of-the-art decentralized methods for MAPF on various metrics. CRAMP improves the solution quality up to 58% measured in makespan and collision count, and up to 5% in success rate in comparison to previous methods.

Learning from human demonstrations (behavior cloning) is a cornerstone of robot learning. However, most behavior cloning algorithms require a large number of demonstrations to learn a task, especially for general tasks that have a large variety of initial conditions. Humans, however, can learn to complete tasks, even complex ones, after only seeing one or two demonstrations. Our work seeks to emulate this ability, using behavior cloning to learn a task given only a single human demonstration. We achieve this goal by using linear transforms to augment the single demonstration, generating a set of trajectories for a wide range of initial conditions. With these demonstrations, we are able to train a behavior cloning agent to successfully complete three block manipulation tasks. Additionally, we developed a novel addition to the temporal ensembling method used by action chunking agents during inference. By incorporating the standard deviation of the action predictions into the ensembling method, our approach is more robust to unforeseen changes in the environment, resulting in significant performance improvements.

Emotions, which are an important component of social interaction, can be studied with the help of android robots and their appearance, which is as similar to humans as possible. The production and customization of android robots is expensive and time-consuming, so it may be practical to use a digital replica. In order to investigate whether there are any perceptual differences in terms of emotions based on the difference in appearance, a robot head was digitally replicated. In an experiment, the basic emotions evaluated in a preliminary study were compared in three conditions and then statistically analyzed. It was found that apart from fear, all emotions were recognized on the real robot head. The digital head with "ideal" emotions performed better than the real head apart from the anger representation, which offers optimization potential for the real head. Contrary to expectations, significant differences between the real and the replicated head with the same emotions could only be found in the representation of surprise.

Improving the overall equipment effectiveness (OEE) of machines on the shop floor is crucial to ensure the productivity and efficiency of manufacturing systems. To achieve the goal of increased OEE, there is a need to develop flexible runtime control strategies for the system. Decentralized strategies, such as multi-agent systems, have proven effective in improving system flexibility. However, runtime multi-agent control of complex manufacturing systems can be challenging as the agents require extensive communication and computational efforts to coordinate agent activities. One way to improve communication speed and cooperation capabilities between system agents is by providing a common language between these agents to represent knowledge about system behavior. The integration of ontology into multi-agent systems in manufacturing provides agents with the capability to continuously update and refine their knowledge in a global context. This paper contributes to the design of an ontology for multi-agent systems in manufacturing, introducing an extendable knowledge base and a methodology for continuously updating the production data by agents during runtime. To demonstrate the effectiveness of the proposed framework, a case study is conducted in a simulated environment, which shows improvements in OEE during runtime.

Human consciousness has been a long-lasting mystery for centuries, while machine intelligence and consciousness is an arduous pursuit. Researchers have developed diverse theories for interpreting the consciousness phenomenon in human brains from different perspectives and levels. This paper surveys several main branches of consciousness theories originating from different subjects including information theory, quantum physics, cognitive psychology, physiology and computer science, with the aim of bridging these theories from a computational perspective. It also discusses the existing evaluation metrics of consciousness and possibility for current computational models to be conscious. Breaking the mystery of consciousness can be an essential step in building general artificial intelligence with computing machines.

Unmanned aerial vehicles (UAVs) are capable of surveying expansive areas, but their operational range is constrained by limited battery capacity. The deployment of mobile recharging stations using unmanned ground vehicles (UGVs) significantly extends the endurance and effectiveness of UAVs. However, optimizing the routes of both UAVs and UGVs, known as the UAV-UGV cooperative routing problem, poses substantial challenges, particularly with respect to the selection of recharging locations. Here in this paper, we leverage reinforcement learning (RL) for the purpose of identifying optimal recharging locations while employing constraint programming to determine cooperative routes for the UAV and UGV. Our proposed framework is then benchmarked against a baseline solution that employs Genetic Algorithms (GA) to select rendezvous points. Our findings reveal that RL surpasses GA in terms of reducing overall mission time, minimizing UAV-UGV idle time, and mitigating energy consumption for both the UAV and UGV. These results underscore the efficacy of incorporating heuristics to assist RL, a method we refer to as heuristics-assisted RL, in generating high-quality solutions for intricate routing problems.

Students' decisions on whether to take a class are strongly affected by whether their friends plan to take the class with them. A student may prefer to be assigned to a course they likes less, just to be with their friends, rather than taking a more preferred class alone. It has been shown that taking classes with friends positively affects academic performance. Thus, academic institutes should prioritize friendship relations when assigning course seats. The introduction of friendship relations results in several non-trivial changes to current course allocation methods. This paper explores how course allocation mechanisms can account for friendships between students and provide a unique, distributed solution. In particular, we model the problem as an asymmetric distributed constraint optimization problem and develop a new dedicated algorithm. Our extensive evaluation includes both simulated data and data derived from a user study on 177 students' preferences over courses and friends. The results show that our algorithm obtains high utility for the students while keeping the solution fair and observing courses' seat capacity limitations.

We introduce a framework for reasoning about the security of computer systems using modal logic. This framework is sufficiently expressive to capture a variety of known security properties, while also being intuitive and independent of syntactic details and enforcement mechanisms. We show how to use our formalism to represent various progress- and termination-(in)sensitive variants of confidentiality, integrity, robust declassification and transparent endorsement, and prove equivalence to standard definitions. The intuitive nature and closeness to semantic reality of our approach allows us to make explicit several hidden assumptions of these definitions, and identify potential issues and subtleties with them, while also holding the promise of formulating cleaner versions and future extension to entirely novel properties.

User behavior analysis is crucial in human-centered AI applications. In this field, the collection of sufficient and high-quality user behavior data has always been a fundamental yet challenging problem. An intuitive idea to address this problem is automatically simulating the user behaviors. However, due to the subjective and complex nature of human cognitive processes, reliably simulating the user behavior is difficult. Recently, large language models (LLM) have obtained remarkable successes, showing great potential to achieve human-like intelligence. We argue that these models present significant opportunities for reliable user simulation, and have the potential to revolutionize traditional study paradigms in user behavior analysis. In this paper, we take recommender system as an example to explore the potential of using LLM for user simulation. Specifically, we regard each user as an LLM-based autonomous agent, and let different agents freely communicate, behave and evolve in a virtual simulator called RecAgent. For comprehensively simulation, we not only consider the behaviors within the recommender system (\emph{e.g.}, item browsing and clicking), but also accounts for external influential factors, such as, friend chatting and social advertisement. Our simulator contains at most 1000 agents, and each agent is composed of a profiling module, a memory module and an action module, enabling it to behave consistently, reasonably and reliably. In addition, to more flexibly operate our simulator, we also design two global functions including real-human playing and system intervention. To evaluate the effectiveness of our simulator, we conduct extensive experiments from both agent and system perspectives. In order to advance this direction, we have released our project at {https://github.com/RUC-GSAI/YuLan-Rec}.

Over the recent years, Reinforcement Learning combined with Deep Learning techniques has successfully proven to solve complex problems in various domains, including robotics, self-driving cars, and finance. In this paper, we are introducing Reinforcement Learning (RL) to label placement, a complex task in data visualization that seeks optimal positioning for labels to avoid overlap and ensure legibility. Our novel point-feature label placement method utilizes Multi-Agent Deep Reinforcement Learning to learn the label placement strategy, the first machine-learning-driven labeling method, in contrast to the existing hand-crafted algorithms designed by human experts. To facilitate RL learning, we developed an environment where an agent acts as a proxy for a label, a short textual annotation that augments visualization. Our results show that the strategy trained by our method significantly outperforms the random strategy of an untrained agent and the compared methods designed by human experts in terms of completeness (i.e., the number of placed labels). The trade-off is increased computation time, making the proposed method slower than the compared methods. Nevertheless, our method is ideal for scenarios where the labeling can be computed in advance, and completeness is essential, such as cartographic maps, technical drawings, and medical atlases. Additionally, we conducted a user study to assess the perceived performance. The outcomes revealed that the participants considered the proposed method to be significantly better than the other examined methods. This indicates that the improved completeness is not just reflected in the quantitative metrics but also in the subjective evaluation by the participants.