Reconstructing indoor map layouts from geometrical data

October 20, 2023 09:16 ,

Matteo Luperto, Francesco Amigoni, Reconstruction and prediction of the layout of indoor environments from two-dimensional metric maps, Engineering Applications of Artificial Intelligence, Volume 113, 2022 DOI: 10.1016/j.engappai.2022.104910.

Metric maps, like occupancy grids, are one of the most common ways to represent indoor environments in autonomous mobile robotics. Although they are effective for navigation and localization, metric maps contain little knowledge about the structure of the buildings they represent. In this paper, we propose a method that identifies the structure of indoor environments from 2D metric maps by retrieving their layout, namely an abstract geometrical representation that models walls as line segments and rooms as polygons. The method works by finding regularities within a building, abstracting from the possibly noisy information of the metric map, and uses such knowledge to reconstruct the layout of the observed part and to predict a possible layout of the partially observed portion of the building. Thus, differently of other methods from the state of the art, our method can be applied both to fully observed environments and, most significantly, to partially observed ones. Experimental results show that our approach performs effectively and robustly on different types of input metric maps and that the predicted layout is increasingly more accurate when the input metric map is increasingly more complete. The layout returned by our method can be exploited in several tasks, such as semantic mapping, place categorization, path planning, human\u2013robot communication, and task allocation.

Posted in: Mobile robot mapping , Tagged:

Increasing exploration when the agent performs worse, decreasing when performing better, in the context of DQN for distributing computation among cloud and edge servers, also dealing with hybridization of RL with Fuzzy

October 20, 2023 09:13 ,

Do Bao Son, Ta Huu Binh, Hiep Khac Vo, Binh Minh Nguyen, Huynh Thi Thanh Binh, Shui Yu, Value-based reinforcement learning approaches for task offloading in Delay Constrained Vehicular Edge Computing, Engineering Applications of Artificial Intelligence, Volume 113, 2022 DOI: 10.1016/j.engappai.2022.104898.

In the age of booming information technology, human-being has witnessed the need for new paradigms with both high computational capability and low latency. A potential solution is Vehicular Edge Computing (VEC). Previous work proposed a Fuzzy Deep Q-Network in Offloading scheme (FDQO) that combines Fuzzy rules and Deep Q-Network (DQN) to improve DQN\u2019s early performance by using Fuzzy Controller (FC). However, we notice that frequent usage of FC can hinder the future growth performance of model. One way to overcome this issue is to remove Fuzzy Controller entirely. We introduced an algorithm called baseline DQN (b-DQN), represented by its two variants Static baseline DQN (Sb-DQN) and Dynamic baseline DQN (Db-DQN), to modify the exploration rate base on the average rewards of closest observations. Our findings confirm that these baseline DQN algorithms surpass traditional DQN models in terms of average Quality of Experience (QoE) in 100 time slots by about 6%, but still suffer from poor early performance (such as in the first 5 time slots). Here, we introduce baseline FDQO (b-FDQO). This algorithm has a strategy to modify the Fuzzy Logic usage instead of removing it entirely while still observing the rewards to modify the exploration rate. It brings a higher average QoE in the first 5 time slots compared to other non-fuzzy-logic algorithms by at least 55.12%, prevent the model from getting too bad result over all time slots, while having the late performance as good as that of b-DQN.

Posted in: Reinforcement learning in AI , Tagged: , ,

Abstraction of continuous control problems considered as MDPs

October 20, 2023 09:03 ,

H. G. Tanner and A. Stager, Data-Driven Abstractions for Robots With Stochastic Dynamics, IEEE Transactions on Robotics, vol. 38, no. 3, pp. 1686-1702, June 2022 DOI: 10.1109/TRO.2021.3119209.

This article describes the construction of stochastic, data-based discrete abstractions for uncertain random processes continuous in time and space. Motivated by the fact that modeling processes often introduce errors which interfere with the implementation of control strategies, here the abstraction process proceeds in reverse: the methodology does not abstract models; rather it models abstractions. Specifically, it first formalizes a template for a family of stochastic abstractions, and then fits the parameters of that template to match the dynamics of the underlying process and ground the abstraction. The article also shows how the parameter-fitting approach can be implemented based on a probabilistic model validation approach which draws from randomized algorithms, and results in a discrete abstract model which is approximately simulated by the actual process physics, at a desired confidence level. In this way, the models afford the implementation of symbolic control plans with probabilistic guarantees at a desired level of fidelity.

Posted in: Control Engineering , Tagged: , ,

Continuous POMDPs through belief state sparsification, applied to active SLAM

October 20, 2023 08:56 ,

Elimelech K, Indelman V. Simplified decision making in the belief space using belief sparsification. The International Journal of Robotics Research. 2022;41(5):470-496 DOI: 10.1177/02783649221076381.

In this work, we introduce a new and efficient solution approach for the problem of decision making under uncertainty, which can be formulated as decision making in a belief space, over a possibly high-dimensional state space. Typically, to solve a decision problem, one should identify the optimal action from a set of candidates, according to some objective. We claim that one can often generate and solve an analogous yet simplified decision problem, which can be solved more efficiently. A wise simplification method can lead to the same action selection, or one for which the maximal loss in optimality can be guaranteed. Furthermore, such simplification is separated from the state inference and does not compromise its accuracy, as the selected action would finally be applied on the original state. First, we present the concept for general decision problems and provide a theoretical framework for a coherent formulation of the approach. We then practically apply these ideas to decision problems in the belief space, which can be simplified by considering a sparse approximation of their initial belief. The scalable belief sparsification algorithm we provide is able to yield solutions which are guaranteed to be consistent with the original problem. We demonstrate the benefits of the approach in the solution of a realistic active-SLAM problem and manage to significantly reduce computation time, with no loss in the quality of solution. This work is both fundamental and practical and holds numerous possible extensions.

Posted in: Mobile robot SLAM , Tagged: , ,

Hybridizing model-free and model-based in continuous RL, and a nice review of current research and benchmarks in robotics

October 20, 2023 08:49 ,

Pinosky A, Abraham I, Broad A, Argall B, Murphey TD. Hybrid control for combining model-based and model-free reinforcement learning The International Journal of Robotics Research. 2023;42(6):337-355 DOI: 10.1177/02783649221083331.

We develop an approach to improve the learning capabilities of robotic systems by combining learned predictive models with experience-based state-action policy mappings. Predictive models provide an understanding of the task and the dynamics, while experience-based (model-free) policy mappings encode favorable actions that override planned actions. We refer to our approach of systematically combining model-based and model-free learning methods as hybrid learning. Our approach efficiently learns motor skills and improves the performance of predictive models and experience-based policies. Moreover, our approach enables policies (both model-based and model-free) to be updated using any off-policy reinforcement learning method. We derive a deterministic method of hybrid learning by optimally switching between learning modalities. We adapt our method to a stochastic variation that relaxes some of the key assumptions in the original derivation. Our deterministic and stochastic variations are tested on a variety of robot control benchmark tasks in simulation as well as a hardware manipulation task. We extend our approach for use with imitation learning methods, where experience is provided through demonstrations, and we test the expanded capability with a real-world pick-and-place task. The results show that our method is capable of improving the performance and sample efficiency of learning motor skills in a variety of experimental domains.

Posted in: Applications of reinforcement learning to robots , Tagged: , , ,

How plans influence sensors

October 13, 2023 09:58 ,

McFassel G, Shell DA. Reactivity and statefulness: Action-based sensors, plans, and necessary state. The International Journal of Robotics Research. 2023;42(6):385-411 DOI: 10.1177/02783649221078874.

Typically to a roboticist, a plan is the outcome of other work, a synthesized object that realizes ends defined by some problem; plans qua plans are seldom treated as first-class objects of study. Plans designate functionality: a plan can be viewed as defining a robot\u2019s behavior throughout its execution. This informs and reveals many other aspects of the robot\u2019s design, including: necessary sensors and action choices, history, state, task structure, and how to define progress. Interrogating sets of plans helps in comprehending the ways in which differing executions influence the interrelationships between these various aspects. Revisiting Erdmann\u2019s theory of action-based sensors, a classical approach for characterizing fundamental information requirements, we show how plans (in their role of designating behavior) influence sensing requirements. Using an algorithm for enumerating plans, we examine how some plans for which no action-based sensor exists can be transformed into sets of sensors through the identification and handling of features that preclude the existence of action-based sensors. We are not aware of those obstructing features having been previously identified. Action-based sensors may be treated as standalone reactive plans; we relate them to the set of all possible plans through a lattice structure. This lattice reveals a boundary between plans with action-based sensors and those without. Some plans, specifically those that are not reactive plans and require some notion of internal state, can never have associated action-based sensors. Even so, action-based sensors can serve as a framework to explore and interpret how such plans make use of state.

Posted in: Robot task planning

POMDPs in robotics: QMDP-Net as a counterpart for the Partially Observable Markov Decision Process (POMDP) whose transition, observation, and reward functions are initially unknown

October 13, 2023 09:55 ,

Collins N, Kurniawati H. Locally connected interrelated network: A forward propagation primitive, The International Journal of Robotics Research. 2023;42(6):371-384 DOI: 10.1177/02783649221093092.

End-to-end learning for planning is a promising approach for finding good robot strategies in situations where the state transition, observation, and reward functions are initially unknown. Many neural network architectures for this approach have shown positive results. Across these networks, seemingly small components have been used repeatedly in different architectures, which means improving the efficiency of these components has great potential to improve the overall performance of the network. This paper aims to improve one such component: The forward propagation module. In particular, we propose Locally Connected Interrelated Network (LCI-Net) \u2013 a novel type of locally connected layer with unshared but interrelated weights \u2013 to improve the efficiency of learning stochastic transition models for planning and propagating information via the learned transition models. LCI-Net is a small differentiable neural network module that can be plugged into various existing architectures. For evaluation purposes, we apply LCI-Net to VIN and QMDP-Net. VIN is an end-to-end neural network for solving Markov Decision Processes (MDPs) whose transition and reward functions are initially unknown, while QMDP-Net is its counterpart for the Partially Observable Markov Decision Process (POMDP) whose transition, observation, and reward functions are initially unknown. Simulation tests on benchmark problems involving 2D and 3D navigation and grasping indicate promising results: Changing only the forward propagation module alone with LCI-Net improves VIN\u2019s and QMDP-Net generalisation capability by more than 3� and 10�, respectively.

Posted in: Applications of reinforcement learning to robots , Tagged: ,

RL in manufacturing control

October 13, 2023 09:49 ,

Vladimir Samsonov, Karim Ben Hicham, Tobias Meisen, Reinforcement Learning in Manufacturing Control: Baselines, challenges and ways forward, Engineering Applications of Artificial Intelligence, Volume 112, 2022 DOI: 10.1016/j.engappai.2022.104868.

The field of Neural Combinatorial Optimization (NCO) offers multiple learning-based approaches to solve well-known combinatorial optimization tasks such as Traveling Salesman or Knapsack problem capable of competing with classical optimization approaches in terms of both solution quality and speed. This brought the attention of the research community to the tasks of Manufacturing Control (MC) with combinatorial nature. In this paper we outline the main components of MC tasks, select the most promising application fields and analyze dedicated learning-based solutions available in the literature. We draw multiple parallels to the current state of the art in the NCO field and allocate the main research gaps and directions on the perception, cognition and interaction levels. Using a set of practical examples we implement and benchmark common design patterns for single-agent Reinforcement Learning (RL) solutions. Along with testing existing solutions, we build on the ranked reward idea (Laterre et al., 2018) and offer a novel Multi-Instance Ranked Reward (m-R2) approach tailored to MC optimization tasks. It minimizes the reward shaping effort and defines a suitable training curriculum for more stable learning by separately tracking the agent\u2019s performance on every scheduling task and rewarding only policies contributing towards better scheduling solutions. We implement all solution design patterns as a set of interchangeable modules with a shared API, unified in a benchmarking framework with the focus on standardization of training and evaluation processes, reproducibility and simplified experiment lifecycle management. In addition to the framework, we make available our discrete-event simulation of a job shop production.

Also:

Zhihao Liu, Quan Liu, Wenjun Xu, Lihui Wang, Zude Zhou,
Robot learning towards smart robotic manufacturing: A review,
Robotics and Computer-Integrated Manufacturing,
Volume 77,
2022,
102360,
ISSN 0736-5845,
https://doi.org/10.1016/j.rcim.2022.102360.

Posted in: Applications of reinforcement learning to control engineering , Tagged:

Dealing with continuous spaces in Q-learning by maintaining several spaces, each one corresponding to a particular time-step

October 13, 2023 09:45 ,

Joao Pedro Araujo, Mario A.T. Figueiredo, Miguel Ayala Botto, Control with adaptive Q-learning: A comparison for two classical control problems, Engineering Applications of Artificial Intelligence, Volume 112, 2022 DOI: 10.1016/j.engappai.2022.104797.

This paper evaluates adaptive Q-learning (AQL) and single-partition adaptive Q-learning (SPAQL), two algorithms for efficient model-free episodic reinforcement learning (RL), in two classical control problems (Pendulum and CartPole). AQL adaptively partitions the state\u2013action space of a Markov decision process (MDP), while learning the control policy, i.e., the mapping from states to actions. The main difference between AQL and SPAQL is that the latter learns time-invariant policies, where the mapping from states to actions does not depend explicitly on the time step. This paper also proposes the SPAQL with terminal state (SPAQL-TS), an improved version of SPAQL tailored for the design of regulators for control problems. The time-invariant policies are shown to result in a better performance than the time-variant ones in both problems studied. These algorithms are particularly fitted to RL problems where the action space is finite, as is the case with the CartPole problem. SPAQL-TS solves the OpenAI GymCartPole problem, while also displaying a higher sample efficiency than trust region policy optimization (TRPO), a standard RL algorithm for solving control tasks. Moreover, the policies learned by SPAQL are interpretable, while TRPO policies are typically encoded as neural networks, and therefore hard to interpret. Yielding interpretable policies while being sample-efficient are the major advantages of SPAQL. The code for the experiments is available at https://github.com/jaraujo98/SinglePartitionAdaptiveQLearning.

Posted in: Reinforcement learning theory , Tagged: , ,

Modifications of Q-learning for better learning of robot navigation

October 13, 2023 09:30 ,

Ee Soong Low, Pauline Ong, Cheng Yee Low, Rosli Omar, Modified Q-learning with distance metric and virtual target on path planning of mobile robot, Expert Systems with Applications, Volume 199, 2022, DOI: 10.1016/j.eswa.2022.117191.

Path planning is an essential element in mobile robot navigation. One of the popular path planners is Q-learning \u2013 a type of reinforcement learning that learns with little or no prior knowledge of the environment. Despite the successful implementation of Q-learning reported in numerous studies, its slow convergence associated with the curse of dimensionality may limit the performance in practice. To solve this problem, an Improved Q-learning (IQL) with three modifications is introduced in this study. First, a distance metric is added to Q-learning to guide the agent moves towards the target. Second, the Q function of Q-learning is modified to overcome dead-ends more effectively. Lastly, the virtual target concept is introduced in Q-learning to bypass dead-ends. Experimental results across twenty types of navigation maps show that the proposed strategies accelerate the learning speed of IQL in comparison with the Q-learning. Besides, performance comparison with seven well-known path planners indicates its efficiency in terms of the path smoothness, time taken, shortest distance and total distance used.

Posted in: Applications of reinforcement learning to robots , Tagged: , ,