Searching for objects: Combining multiple cues to object locations using a maximum entropy model

Abstract

Abstract-In this paper, we consider the problem of how background knowledge about usual object arrangements can be utilized by a mobile robot to more efficiently find an object in an unknown environment. We decompose the action selection problem during the search into two parts. First, we compute a belief over the location of the object and subsequently use the belief to select the next target location the robot should visit. For the inference part, we utilize a maximum entropy model which models the conditional distribution over possible locations of the target object given the observations made so far. The model is based on co-occurrences of objects and object attributes in different spatial contexts. The parameters are learned by maximizing the data likelihood using gradient ascent. We evaluate our approach by simulated search runs based on data obtained from different real-world environments. Our results show a significant improvement over a standard search technique which does not employ domain-specific background knowledge.

Active Object Search Exploiting Probabilistic Object–Object Relations

“…For selecting the room to which to navigate, the decision-theoretic approach introduced in [11] is adopted. For determining to which object to navigate inside that room, an expected utility, inspired by [11,7], that combines the probability of successfully finding the target object with the travel cost is maximized:…”

“…The application in [7,8] is finding target objects in a supermarket. Objectobject attribute relations are used, rather then object-room relations, e.g., 'an avocado will probably be located somewhere where other fruit can be found' or 'pizza can be found in a freezer'.…”

Searching objects in large-scale indoor environments: A decision-theoretic approach

“…How to use semantic knowledge within object search tasks is explored by [9], [10], [11]. Our approach can be considered in a similar line of research.…”

“…Our approach can be considered in a similar line of research. Probabilistic models are used in [9] to guide a simulated robot during object search tasks in structured indoor environments, namely supermarkets. Work by [10] utilizes also probabilistic methods on a robot system to make inferences about the spatial relations between object instances in the environment.…”

Development of A Behavior‐Based Cooperative Search Strategy for Distributed Autonomous Mobile Robots Using Zigbee Wireless Sensor Network

“…Although diverse strategies have been developed for search tasks , the randomized search strategy is extensively adopted in real‐world applications due to its relatively easy and low‐cost implementation . However, this strategy randomly drives distributed mobile robots without ensuring search efficiency, which is significantly affected by the cooperative strategy developed with multiple behaviors.…”