Nikhil Deshpande

Learn More
Reinforcement learning, in general, has not been totally successful at solving complex real-world problems which can be described by nonlinear functions. However, temporal difference learning is a type of reinforcement learning algorithm that has been researched and applied to various prediction problems with promising results. This paper discusses the(More)
— We propose that robot perception is enabled by means of a common sensorimotor semantics arising from a set of symmetry theories (expressed as symmetry detectors and parsers) embedded a priori in each robot. These theories inform the production of structural representations of sensorimotor processes, and these representations, in turn, permit perceptual(More)
—Autonomous mobile robots (AMRs) operating in unknown environments face twin challenges: 1) localization and 2) efficient directed navigation. This paper describes a two-tiered approach to solving these challenges: 1) by developing novel wireless-sensor-network (WSN)-based localization methods and 2) by using WSN–AMR interaction for navigation. The goal is(More)
Given a set of unknown sensors and actuators, sensorimotor reconstruction is achieved by exploiting relations between the sensor data and the actuator control data to determine sets of similar sensors, sets of similar actuators, necessary relations between them, as well as sensorimotor relations to the environment. Several authors have addressed this(More)
— Robot manipulator designs are increasingly fo-cused on low cost approaches, especially those envisioned for use in unstructured environments such as households, office spaces and hazardous environments. The cost of angular sensors varies based on the precision offered. For tasks in these environments, millimeter order manipulation errors are unlikely to(More)
The colossal amount of digitized information available has resulted in overloading users who need to navigate this information for their routine requirements. Information filtering deals with monitoring text streams to detect patterns and retrieval of documents by searching for patterns over stored data. Although information filtering systems and search(More)
—This paper extends the novel research for event localization and target-directed navigation using a deployed wireless sensor network (WSN) [4]. The goal is to have an autonomous mobile robot (AMR) navigate to a target-location by: (i) producing an artificial magnitude distribution within the WSN-covered region, and (ii) having the AMR use the(More)