This study explores the problem of Multi-Agent Path Finding with continuous and stochastic travel times whose probability distribution is unknown. Our purpose is to manage a group of automated robots that provide package delivery services in a building where pedestrians and a wide variety of robots coexist, such as delivery services in office buildings, hospitals, and apartments. It is often the case with these real-world applications that the time required for the robots to traverse a corridor takes a continuous value and is randomly distributed, and the prior knowledge of the probability distribution of the travel time is limited. Multi-Agent Path Finding has been widely studied and applied to robot management systems; however, automating the robot operation in such environments remains difficult. We propose 1) online re-planning to update the action plan of robots while it is executed, and 2) parameter update to estimate the probability distribution of travel time using Bayesian inference as the delay is observed. We use a greedy heuristic to obtain solutions in a limited computation time. Through simulations, we empirically compare the performance of our method to those of existing methods in terms of the conflict probability and the actual travel time of robots. The simulation results indicate that the proposed method can find travel paths with at least 50% fewer conflicts and a shorter actual total travel time than existing methods. The proposed method requires a small number of trials to achieve the performance because the parameter update is prioritized on the important edges for path planning, thereby satisfying the requirements of quick implementation of robust planning of automated delivery services.
相關內容
In distributed model predictive control (MPC), the control input at each sampling time is computed by solving a large-scale optimal control problem (OCP) over a finite horizon using distributed algorithms. Typically, such algorithms require several (virtually, infinite) communication rounds between the subsystems to converge, which is a major drawback both computationally and from an energetic perspective (for wireless systems). Motivated by these challenges, we propose a suboptimal distributed MPC scheme in which the total communication burden is distributed also in time, by maintaining a running solution estimate for the large-scale OCP and updating it at each sampling time. We demonstrate that, under some regularity conditions, the resulting suboptimal MPC control law recovers the qualitative robust stability properties of optimal MPC, if the communication budget at each sampling time is large enough.
Federated Learning (FL) has recently emerged as a popular framework, which allows resource-constrained discrete clients to cooperatively learn the global model under the orchestration of a central server while storing privacy-sensitive data locally. However, due to the difference in equipment and data divergence of heterogeneous clients, there will be parameter deviation between local models, resulting in a slow convergence rate and a reduction of the accuracy of the global model. The current FL algorithms use the static client learning strategy pervasively and can not adapt to the dynamic training parameters of different clients. In this paper, by considering the deviation between different local model parameters, we propose an adaptive learning rate scheme for each client based on entropy theory to alleviate the deviation between heterogeneous clients and achieve fast convergence of the global model. It's difficult to design the optimal dynamic learning rate for each client as the local information of other clients is unknown, especially during the local training epochs without communications between local clients and the central server. To enable a decentralized learning rate design for each client, we first introduce mean-field schemes to estimate the terms related to other clients' local model parameters. Then the decentralized adaptive learning rate for each client is obtained in closed form by constructing the Hamilton equation. Moreover, we prove that there exist fixed point solutions for the mean-field estimators, and an algorithm is proposed to obtain them. Finally, extensive experimental results on real datasets show that our algorithm can effectively eliminate the deviation between local model parameters compared to other recent FL algorithms.
Large neural networks can improve the accuracy and generalization on tasks across many domains. However, this trend cannot continue indefinitely due to limited hardware memory. As a result, researchers have devised a number of memory optimization methods (MOMs) to alleviate the memory bottleneck, such as gradient checkpointing, quantization, and swapping. In this work, we study memory optimization methods and show that, although these strategies indeed lower peak memory usage, they can actually decrease training throughput by up to 9.3x. To provide practical guidelines for practitioners, we propose a simple but effective performance model PAPAYA to quantitatively explain the memory and training time trade-off. PAPAYA can be used to determine when to apply the various memory optimization methods in training different models. We outline the circumstances in which memory optimization techniques are more advantageous based on derived implications from PAPAYA. We assess the accuracy of PAPAYA and the derived implications on a variety of machine models, showing that it achieves over 0.97 R score on predicting the peak memory/throughput, and accurately predicts the effectiveness of MOMs across five evaluated models on vision and NLP tasks.
In recent years there has been great progress in the use of machine learning algorithms to develop interatomic potential models. Machine-learned potential models are typically orders of magnitude faster than density functional theory but also orders of magnitude slower than physics-derived models such as the embedded atom method. In our previous work, we used symbolic regression to develop fast, accurate and transferrable interatomic potential models for copper with novel functional forms that resemble those of the embedded atom method. To determine the extent to which the success of these forms was specific to copper, here we explore the generalizability of these models to other face-centered cubic transition metals and analyze their out-of-sample performance on several material properties. We found that these forms work particularly well on elements that are chemically similar to copper. When compared to optimized Sutton-Chen models, which have similar complexity, the functional forms discovered using symbolic regression perform better across all elements considered except gold where they have a similar performance. They perform similarly to a moderately more complex embedded atom form on properties on which they were trained, and they are more accurate on average on other properties. We attribute this improved generalized accuracy to the relative simplicity of the models discovered using symbolic regression. The genetic programming models are found to outperform other models from the literature about 50% of the time in a variety of property predictions, with about 1/10th the model complexity on average. We discuss the implications of these results to the broader application of symbolic regression to the development of new potentials and highlight how models discovered for one element can be used to seed new searches for different elements.
Robot manipulation in cluttered scenes often requires contact-rich interactions with objects. It can be more economical to interact via non-prehensile actions, for example, push through other objects to get to the desired grasp pose, instead of deliberate prehensile rearrangement of the scene. For each object in a scene, depending on its properties, the robot may or may not be allowed to make contact with, tilt, or topple it. To ensure that these constraints are satisfied during non-prehensile interactions, a planner can query a physics-based simulator to evaluate the complex multi-body interactions caused by robot actions. Unfortunately, it is infeasible to query the simulator for thousands of actions that need to be evaluated in a typical planning problem as each simulation is time-consuming. In this work, we show that (i) manipulation tasks (specifically pick-and-place style tasks from a tabletop or a refrigerator) can often be solved by restricting robot-object interactions to adaptive motion primitives in a plan, (ii) these actions can be incorporated as subgoals within a multi-heuristic search framework, and (iii) limiting interactions to these actions can help reduce the time spent querying the simulator during planning by up to 40x in comparison to baseline algorithms. Our algorithm is evaluated in simulation and in the real-world on a PR2 robot using PyBullet as our physics-based simulator. Supplementary video: \url{//youtu.be/ABQc7JbeJPM}.
Real-world manipulation problems in heavy clutter require robots to reason about potential contacts with objects in the environment. We focus on pick-and-place style tasks to retrieve a target object from a shelf where some `movable' objects must be rearranged in order to solve the task. In particular, our motivation is to allow the robot to reason over and consider non-prehensile rearrangement actions that lead to complex robot-object and object-object interactions where multiple objects might be moved by the robot simultaneously, and objects might tilt, lean on each other, or topple. To support this, we query a physics-based simulator to forward simulate these interaction dynamics which makes action evaluation during planning computationally very expensive. To make the planner tractable, we establish a connection between the domain of Manipulation Among Movable Objects and Multi-Agent Pathfinding that lets us decompose the problem into two phases our M4M algorithm iterates over. First we solve a multi-agent planning problem that reasons about the configurations of movable objects but does not forward simulate a physics model. Next, an arm motion planning problem is solved that uses a physics-based simulator but does not search over possible configurations of movable objects. We run simulated and real-world experiments with the PR2 robot and compare against relevant baseline algorithms. Our results highlight that M4M generates complex 3D interactions, and solves at least twice as many problems as the baselines with competitive performance.
Control Barrier Functions offer safety certificates by dictating controllers that enforce safety constraints. However, their response depends on the classK function that is used to restrict the rate of change of the barrier function along the system trajectories. This paper introduces the notion of Rate Tunable Control Barrier Function (RT-CBF), which allows for online tuning of the response of CBF-based controllers. In contrast to the existing CBF approaches that use a fixed (predefined) classK function to ensure safety, we parameterize and adapt the classK function parameters online. Furthermore, we discuss the challenges associated with multiple barrier constraints, namely ensuring that they admit a common control input that satisfies them simultaneously for all time. In practice, RT-CBF enables designing parameter dynamics for (1) a better-performing response, where performance is defined in terms of the cost accumulated over a time horizon, or (2) a less conservative response. We propose a model-predictive framework that computes the sensitivity of the future states with respect to the parameters and uses Sequential Quadratic Programming for deriving an online law to update the parameters in the direction of improving the performance. When prediction is not possible, we also provide point-wise sufficient conditions to be imposed on any user-given parameter dynamics so that multiple CBF constraints continue to admit common control input with time. Finally, we introduce RT-CBFs for decentralized uncooperative multi-agent systems, where a trust factor, computed based on the instantaneous ease of constraint satisfaction, is used to update parameters online for a less conservative response.
The conditional moment problem is a powerful formulation for describing structural causal parameters in terms of observables, a prominent example being instrumental variable regression. A standard approach reduces the problem to a finite set of marginal moment conditions and applies the optimally weighted generalized method of moments (OWGMM), but this requires we know a finite set of identifying moments, can still be inefficient even if identifying, or can be theoretically efficient but practically unwieldy if we use a growing sieve of moment conditions. Motivated by a variational minimax reformulation of OWGMM, we define a very general class of estimators for the conditional moment problem, which we term the variational method of moments (VMM) and which naturally enables controlling infinitely-many moments. We provide a detailed theoretical analysis of multiple VMM estimators, including ones based on kernel methods and neural nets, and provide conditions under which these are consistent, asymptotically normal, and semiparametrically efficient in the full conditional moment model. We additionally provide algorithms for valid statistical inference based on the same kind of variational reformulations, both for kernel- and neural-net-based varieties. Finally, we demonstrate the strong performance of our proposed estimation and inference algorithms in a detailed series of synthetic experiments.
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.
We describe ACE0, a lightweight platform for evaluating the suitability and viability of AI methods for behaviour discovery in multiagent simulations. Specifically, ACE0 was designed to explore AI methods for multi-agent simulations used in operations research studies related to new technologies such as autonomous aircraft. Simulation environments used in production are often high-fidelity, complex, require significant domain knowledge and as a result have high R&D costs. Minimal and lightweight simulation environments can help researchers and engineers evaluate the viability of new AI technologies for behaviour discovery in a more agile and potentially cost effective manner. In this paper we describe the motivation for the development of ACE0.We provide a technical overview of the system architecture, describe a case study of behaviour discovery in the aerospace domain, and provide a qualitative evaluation of the system. The evaluation includes a brief description of collaborative research projects with academic partners, exploring different AI behaviour discovery methods.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191