Sanem Sariel

Bio: Sanem Sariel is an academic researcher from Istanbul Technical University. The author has contributed to research in topics: Robot & Task (project management). The author has an hindex of 13, co-authored 51 publications receiving 604 citations. Previous affiliations of Sanem Sariel include University of Plymouth.

Naval Mine Countermeasure Missions

Abstract: Undersea operations using autonomous underwater vehicles (AUVs) provide a different and in some ways a more challenging problem than tasks for unmanned aerial vehicles and unmanned ground vehicles. In particular, in undersea operations, communication windows are restricted, and bandwidth is limited. Consequently, coordination among agents is correspondingly more difficult. In traditional approaches, a central planner initially assigns subtasks to a set of AUVs to achieve the team goal. However, those initial task assignments may become inefficient during real-time execution because of the real-world issues such as failures. Therefore, initial task allocations are usually subject to change if efficiency is a high concern. Reallocations are needed and should be performed in a distributed manner. To provide such flexibility, we propose a distributed auction-based cooperation framework, distributed and efficient multirobot-cooperation framework (DEMiR-CF), which is an online dynamic task allocation (reallocation) system that aims to achieve a team goal while using resources effectively. DEMiR-CF, with integrated task scheduling and execution capabilities, can also respond to and recover from real-time contingencies such as communication failures, delays, range limitations, and robot failures.

Real time auction based allocation of tasks for multi-robot exploration problem in dynamic environments

Abstract: Single auction-based methods are known to be efficient for multi-robot problem solving. In this work, we investigate performance of our general multi robot coordination framework for multi robot multi target exploration problem under uncertainties in dynamic environments. Our framework offers a real time single item allocation method featuring different mechanisms for failure recovery. In multi robot exploration problem, a different version of well known NP-hard MTSP (Multiple Traveling Salesman Problem), each target is visited by at least one robot in its open tour. Overall objective function for cost optimization while visiting targets varies by different exploration domains. In this work, we present performance results for total cost minimization objective. There are many efficient centralized heuristic methods for generating close to optimal solutions. These heuristics may be used to allocate targets to robots. However, when the environment is dynamic and/or unknown, initially assigned targets may need to be reallocated during run time. In our framework, redundant calculations are eliminated by means of incremental assignments based on up-to-date situations of the environment. Offered precautions in the framework maintain the quality of solutions as close to optimal as possible. Experiments are conducted on simulations. The comparison of the proposed method is made with Prim

Efficient Bids on Task Allocation for Multi-Robot Exploration.

Abstract: We propose a real time single item auction based task allocation method for the multi-robot exploration problem and investigate new bid evaluation strategies in this domain. In this problem, a different version of the well known NP-hard MTSP (Multiple Traveling Salesman Problem), each target must be visited by at least one robot in its open tour. Various objectives may be defined for this problem (e.g. minimization of total path length, time). In this article, we present an extensive analysis of our bid evaluation strategies for minimization of total path length objective. An integer programming (IP) approach may be used to allocate tasks to robots. However, IP approach may become impractical when the size of the mission is not small, the environment is dynamic or unknown, or the structure of the mission changes by online tasks. In real world domains, initial allocations assigned by computationally expensive methods are usually subject to change during run time. Our framework, capable of handling diverse contingencies, performs an incremental allocation method based on the up-to-date situations of the environment. Experimental results in simulations compared to both the results of the Prim Allocation method and the optima reveal efficiency of the bid evaluation heuristics combined with our framework.

A Distributed Multi-robot Cooperation Framework for Real Time Task Achievement

Abstract: In this paper, we propose a general framework, DEMiR-CF, for a multi-robot team to achieve a complex mission including inter-related tasks that require diverse capabilities and/or simultaneous executions. Our framework integrates a distributed task allocation scheme, cooperation mechanisms and precaution routines for multi-robot team execution. Its performance has been demonstrated in NavalMine Countermeasures, Multi-robotMulti-Target Exploration and Object Construction domains. The framework not only ensures near-optimal solutions for task achievement but also efficiently responds to real time contingencies.

Cognition-Enabled Robot Manipulation in Human Environments: Requirements, Recent Work, and Open Problems

Abstract: Service robots are expected to play an important role in our daily lives as our companions in home and work environments in the near future. An important requirement for fulfilling this expectation is to equip robots with skills to perform everyday manipulation tasks, the success of which is crucial for most home chores, such as cooking, cleaning, and shopping. Robots have been used successfully for manipulation tasks in wellstructured and controlled factory environments for decades. Designing skills for robots working in uncontrolled human environments raises many potential challenges in various subdisciplines, such as computer vision, automated planning, and human-robot interaction. In spite of the recent progress in these fields, there are still challenges to tackle. This article outlines problems in different research areas related to mobile manipulation from the cognitive perspective, reviews recently published works and the state-of-the-art approaches to address these problems, and discusses open problems to be solved to realize robot assistants that can be used in manipulation tasks in unstructured human environments.

A sensorimotor account of vision and visual consciousness-Authors' Response-Acting out our sensory experience

Abstract: Many current neurophysiological, psychophysical, and psychological approaches to vision rest on the idea that when we see, the brain produces an internal representation of the world. The activation of this internal representation is assumed to give rise to the experience of seeing. The problem with this kind of approach is that it leaves unexplained how the existence of such a detailed internal representation might produce visual consciousness. An alternative proposal is made here. We propose that seeing is a way of acting. It is a particular way of exploring the environment. Activity in internal representations does not generate the experience of seeing. The outside world serves as its own, external, representation. The experience of seeing occurs when the organism masters what we call the governing laws of sensorimotor contingency. The advantage of this approach is that it provides a natural and principled way of accounting for visual consciousness, and for the differences in the perceived quality of sensory experience in the different sensory modalities. Several lines of empirical evidence are brought forward in support of the theory, in particular: evidence from experiments in sensorimotor adaptation, visual \"filling in,\" visual stability despite eye movements, change blindness, sensory substitution, and color perception.

Consensus-Based Decentralized Auctions for Robust Task Allocation

Abstract: This paper addresses task allocation to coordinate a fleet of autonomous vehicles by presenting two decentralized algorithms: the consensus-based auction algorithm (CBAA) and its generalization to the multi-assignment problem, i.e., the consensus-based bundle algorithm (CBBA). These algorithms utilize a market-based decision strategy as the mechanism for decentralized task selection and use a consensus routine based on local communication as the conflict resolution mechanism to achieve agreement on the winning bid values. Under reasonable assumptions on the scoring scheme, both of the proposed algorithms are proven to guarantee convergence to a conflict-free assignment, and it is shown that the converged solutions exhibit provable worst-case performance. It is also demonstrated that CBAA and CBBA produce conflict-free feasible solutions that are robust to both inconsistencies in the situational awareness across the fleet and variations in the communication network topology. Numerical experiments confirm superior convergence properties and performance when compared with existing auction-based task-allocation algorithms.

Multiagent systems: a modern approach to distributed artificial intelligence

Abstract: Multiagent Systems is the title of a collection of papers dedicated to surveying specific themes of Multiagent Systems (MAS) and Distributed Artificial Intelligence (DAI). All of them authored by leading researchers of this dynamic multidisciplinary field.

A Survey and Analysis of Multi-Robot Coordination

Abstract: In the field of mobile robotics, the study of multi-robot systems (MRSs) has grown significantly in size and importance in recent years. Having made great progress in the development of the basic problems concerning single-robot control, many researchers shifted their focus to the study of multi-robot coordination. This paper presents a systematic survey and analysis of the existing literature on coordination, especially in multiple mobile robot systems (MMRSs). A series of related problems have been reviewed, which include a communication mechanism, a planning strategy and a decision-making structure. A brief conclusion and further research perspectives are given at the end of the paper.

Model-Based Reinforcement Learning for Atari

Abstract: Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in fact, than a human would need to learn the same games. How can people learn so quickly? Part of the answer may be that people can learn how the game works and predict which actions will lead to desirable outcomes. In this paper, we explore how video prediction models can similarly enable agents to solve Atari games with fewer interactions than model-free methods. We describe Simulated Policy Learning (SimPLe), a complete model-based deep RL algorithm based on video prediction models and present a comparison of several model architectures, including a novel architecture that yields the best results in our setting. Our experiments evaluate SimPLe on a range of Atari games in low data regime of 100k interactions between the agent and the environment, which corresponds to two hours of real-time play. In most games SimPLe outperforms state-of-the-art model-free algorithms, in some games by over an order of magnitude.