In this paper we deal with a practical problem that arises in military situations. The problem is to plan a path for one, or more, agents to reach a target without being detected by enemy sensors. Agents are not passive, rather they can initiate actions which aid evasion. They can knockout, completely disable, sensors. They can also confuse sensors, so reduce sensor detection probabilities. Agent actions are path dependent and time limited. By path dependent we mean that an agent needs to be sufficiently close to a sensor to knock it out. By time limited we mean that a limit is imposed on how long a sensor is knocked out or confused before it reverts back to its original operating state. The approach adopted breaks the continuous space in which agents move into a discrete space. This enables the problem to be formulated as a zero-one integer program with linear constraints. The advantage of representing the problem in this manner is that powerful commercial software optimisation packages exist to solve the problem to proven global optimality. A heuristic for the problem based on successive shortest paths is also presented. Computational results are presented for a number of randomly generated test problems.
相關內容
One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of model-based agents is not well understood because existing work has focused on model-free agents when benchmarking generalization. Here, we explicitly measure the generalization ability of model-based agents in comparison to their model-free counterparts. We focus our analysis on MuZero (Schrittwieser et al., 2020), a powerful model-based agent, and evaluate its performance on both procedural and task generalization. We identify three factors of procedural generalization -- planning, self-supervised representation learning, and procedural data diversity -- and show that by combining these techniques, we achieve state-of-the art generalization performance and data efficiency on Procgen (Cobbe et al., 2019). However, we find that these factors do not always provide the same benefits for the task generalization benchmarks in Meta-World (Yu et al., 2019), indicating that transfer remains a challenge and may require different approaches than procedural generalization. Overall, we suggest that building generalizable agents requires moving beyond the single-task, model-free paradigm and towards self-supervised model-based agents that are trained in rich, procedural, multi-task environments.
Recent evidence suggests that SARS-CoV-2, which is the virus causing a global pandemic in 2020, is predominantly transmitted via airborne aerosols in indoor environments. This calls for novel strategies when assessing and controlling a building's indoor air quality (IAQ). IAQ can generally be controlled by ventilation and/or policies to regulate human-building-interaction. However, in a building, occupants use rooms in different ways, and it may not be obvious which measure or combination of measures leads to a cost- and energy-effective solution ensuring good IAQ across the entire building. Therefore, in this article, we introduce a novel agent-based simulator, ArchABM, designed to assist in creating new or adapt existing buildings by estimating adequate room sizes, ventilation parameters and testing the effect of policies while taking into account IAQ as a result of complex human-building interaction patterns. A recently published aerosol model was adapted to calculate time-dependent carbon dioxide ($CO_2$) and virus quanta concentrations in each room and inhaled $CO_2$ and virus quanta for each occupant over a day as a measure of physiological response. ArchABM is flexible regarding the aerosol model and the building layout due to its modular architecture, which allows implementing further models, any number and size of rooms, agents, and actions reflecting human-building interaction patterns. We present a use case based on a real floor plan and working schedules adopted in our research center. This study demonstrates how advanced simulation tools can contribute to improving IAQ across a building, thereby ensuring a healthy indoor environment.
An informative measurement is the most efficient way to gain information about an unknown state. We give a first-principles derivation of a general-purpose dynamic programming algorithm that returns a sequence of informative measurements by sequentially maximizing the entropy of possible measurement outcomes. This algorithm can be used by an autonomous agent or robot to decide where best to measure next, planning a path corresponding to an optimal sequence of informative measurements. This algorithm is applicable to states and controls that are continuous or discrete, and agent dynamics that is either stochastic or deterministic; including Markov decision processes. Recent results from approximate dynamic programming and reinforcement learning, including on-line approximations such as rollout and Monte Carlo tree search, allow an agent or robot to solve the measurement task in real-time. The resulting near-optimal solutions include non-myopic paths and measurement sequences that can generally outperform, sometimes substantially, commonly-used greedy heuristics such as maximizing the entropy of each measurement outcome. This is demonstrated for a global search problem, where on-line planning with an extended local search is found to reduce the number of measurements in the search by half.
Artificial Intelligence has now taken centre stage in the smartphone industry owing to the need of bringing all processing close to the user and addressing privacy concerns. Convolution Neural Networks (CNNs), which are used by several AI applications, are highly resource and computation intensive. Although new generation smartphones come with AI-enabled chips, minimal memory and energy utilisation is essential as many applications are run concurrently on a smartphone. In light of this, optimising the workload on the smartphone by offloading a part of the processing to a cloud server is an important direction of research. In this paper, we analyse the feasibility of splitting CNNs between smartphones and cloud server by formulating a multi-objective optimisation problem that optimises the end-to-end latency, memory utilisation, and energy consumption. We design SmartSplit, a Genetic Algorithm with decision analysis based approach to solve the optimisation problem. Our experiments run with multiple CNN models show that splitting a CNN between a smartphone and a cloud server is feasible. The proposed approach, SmartSplit fares better when compared to other state-of-the-art approaches.
The sampling-based motion planning algorithms can solve the motion planning problem in high-dimensional state space efficiently. This article presents a novel approach to sample in the promising region and reduce planning time remarkably. The RRT# defines the Relevant Region according to the cost-to-come provided by the optimal forward-searching tree; however, it takes the cumulative cost of a direct connection between the current state and the goal state as the cost-to-go. We propose a batch sampling method that samples in the refined Relevant Region, which is defined according to the optimal cost-to-come and the adaptive cost-to-go. In our method, the cost-to-come and the cost-to-go of a specific vertex are estimated by the valid optimal forward-searching tree and the lazy reverse-searching tree, respectively. New samples are generated with a direct sampling method, which can take advantage of the heuristic estimation result. We carry on several simulations in both SE(2) and SE(3) state spaces to validate the effectiveness of our method. Simulation results demonstrate that the proposed algorithm can find a better initial solution and consumes less planning time than related work.
With technological advancement, drone has emerged as unmanned aerial vehicle that can be controlled by humans to fly or reach a destination. This may be autonomous as well, where the drone itself is intelligent enough to find a shortest obstacle-free path to reach the destination from a designated source. Be it a planned smart city or even a wreckage site affected by natural calamity, we may imagine the buildings, any surface-erected structure or other blockage as obstacles for the drone to fly in a direct line-of-sight path. So, the whole bird's eye-view of the landscape can be transformed to a graph of grid-cells, where some are occupied to indicate the obstacles and some are free to indicate the free path. The autonomous drone (AutoDrone) will be able to find out the shortest hindrance-free path while travelling in two-dimensional space and move from one place to another. In this paper, we propose a method to find out an obstacle-free shortest path in the coordinate system guided by GPS. This can be especially beneficial in rescue operations and fast delivery or pick-up in an energy-efficient way, where our algorithm will help in finding out the shortest path and angle along which it should fly. Our work shows different scenarios to path-tracing, through the shortest feasible path computed by the autonomous drone.
A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors. We hypothesize that many of these hidden factors in the physical world are constant over time, changing only sparsely. Accordingly, we propose Gated $L_0$ Regularized Dynamics (GateL0RD), a novel recurrent architecture that incorporates the inductive bias to maintain stable, sparsely changing latent states. The bias is implemented by means of a novel internal gating function and a penalty on the $L_0$ norm of latent state changes. We demonstrate that GateL0RD can compete with or outperform state-of-the-art RNNs in a variety of partially observable prediction and control tasks. GateL0RD tends to encode the underlying generative factors of the environment, ignores spurious temporal dependencies, and generalizes better, improving sampling efficiency and prediction accuracy as well as behavior in model-based planning and reinforcement learning tasks. Moreover, we show that the developing latent states can be easily interpreted, which is a step towards better explainability in RNNs.
Many important real-world problems have action spaces that are high-dimensional, continuous or both, making full enumeration of all possible actions infeasible. Instead, only small subsets of actions can be sampled for the purpose of policy evaluation and improvement. In this paper, we propose a general framework to reason in a principled way about policy evaluation and improvement over such sampled action subsets. This sample-based policy iteration framework can in principle be applied to any reinforcement learning algorithm based upon policy iteration. Concretely, we propose Sampled MuZero, an extension of the MuZero algorithm that is able to learn in domains with arbitrarily complex action spaces by planning over sampled actions. We demonstrate this approach on the classical board game of Go and on two continuous control benchmark domains: DeepMind Control Suite and Real-World RL Suite.
We present Neural A*, a novel data-driven search method for path planning problems. Despite the recent increasing attention to data-driven path planning, a machine learning approach to search-based planning is still challenging due to the discrete nature of search algorithms. In this work, we reformulate a canonical A* search algorithm to be differentiable and couple it with a convolutional encoder to form an end-to-end trainable neural network planner. Neural A* solves a path planning problem by encoding a problem instance to a guidance map and then performing the differentiable A* search with the guidance map. By learning to match the search results with ground-truth paths provided by experts, Neural A* can produce a path consistent with the ground truth accurately and efficiently. Our extensive experiments confirmed that Neural A* outperformed state-of-the-art data-driven planners in terms of the search optimality and efficiency trade-off, and furthermore, successfully predicted realistic human trajectories by directly performing search-based planning on natural image inputs.
Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the pre-processing perception system while the supervised learning-based models are limited by the accessibility of extensive human experience. We present a general and principled Controllable Imitative Reinforcement Learning (CIRL) approach which successfully makes the driving agent achieve higher success rates based on only vision inputs in a high-fidelity car simulator. To alleviate the low exploration efficiency for large continuous action space that often prohibits the use of classical RL on challenging real tasks, our CIRL explores over a reasonably constrained action space guided by encoded experiences that imitate human demonstrations, building upon Deep Deterministic Policy Gradient (DDPG). Moreover, we propose to specialize adaptive policies and steering-angle reward designs for different control signals (i.e. follow, straight, turn right, turn left) based on the shared representations to improve the model capability in tackling with diverse cases. Extensive experiments on CARLA driving benchmark demonstrate that CIRL substantially outperforms all previous methods in terms of the percentage of successfully completed episodes on a variety of goal-directed driving tasks. We also show its superior generalization capability in unseen environments. To our knowledge, this is the first successful case of the learned driving policy through reinforcement learning in the high-fidelity simulator, which performs better-than supervised imitation learning.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191