The JPL BioSleeve is a wearable gesture-based human interface for natural robot control. Activity of the user's hand and arm is monitored via surface electromyography sensors and an inertial measurement unit that are embedded in a forearm sleeve. Gesture recognition software then decodes the sensor signals, classifies gesture type, and maps the result to output commands to be sent to a robot. The BioSleeve interface can accurately and reliably decode as many as sixteen discrete hand and finger gestures and estimate the continuous orientation of the forearm. Here we report development of a new wireless BioSleeve prototype that enables portable field use. Gesture-based commands were developed to control a QinetiQ Dragon Runner tracked robot, including a 4 degree-of-freedom manipulator and a stereo camera pair. Gestures can be sent in several modes: for supervisory point-to-goal driving commands, virtual joystick for teleoperation of driving and manipulator, and pan-tilt of the camera. Hand gestures and arm positions are mapped to various commands recognized by the robot's onboard control software, and are meant to integrate with the robot's perception of its environment and its ability to complete tasks with various levels of autonomy. The portable BioSleeve interface was demonstrated through control of the Dragon Runner during participation in field trials at the 2014 Intuitive Robotic Operator Control Challenge. The successful completion of Challenge events demonstrated the versatility of the system to provide multiple commands in different modes of control to a robot operating under difficult real-world environmental conditions.

Recent studies have proposed the use of a hot-air (Montgolfiere) balloon for possible exploration of Titan, Mars, and Venus. One of NASA's Outer Planet Flagship mission concepts is the Titan Saturn System Mission, which would be a joint NASA-ESA partnership that plans to employ a Montgolfiere along with a lake lander and an orbiter. This Montgolfiere would circle Titan, investigating how Titan and Saturn operate as a system and determining how far prebiotic chemistry has developed. This paper provides a new method to analyze global path planning with balloons on Titan. The main objective of this study is to determine whether the balloon could reach a particular location of interest from a given initial position at its insertion point in the atmosphere using the wind fields on Titan. This study is the first comprehensive analysis and quantitative assessment of balloon guidance in Titan that proactively uses wind for global path planning. The paper will investigate and characterize the guidance and path-planning performance of Montgolfiere balloons in Titan's atmosphere for lower atmosphere and surface exploration in the presence of variable wind fields using the Titan Weather Research and Forecasting (TitanWRF) model. The study focuses on determining the altitude profile that a balloon could follow, using variable wind fields, in order to reach its target most quickly. Our results show that a simple unpropelled Montgolfiere without horizontal actuation would be able to reach a broad array of science targets within the constraints of the wind field. The study also indicates that even a small amount of horizontal thrust allows the balloon to reach any area of interest on Titan, in a fraction of the time needed by the unpropelled balloon. The results show that using the Titan wind field allows a balloon to significantly extend its scientific reach and that a Montgolfiere (unpropelled or propelled) is a highly desirable architecture that can significantly enhance the scientific return of a future Titan mission.

This paper presents a new gesture-based human interface for natural robot control. Detailed activity of the user's hand and arm is acquired via a novel device, called the BioSleeve, which packages dry-contact surface electromyography (EMG) and an inertial measurement unit (IMU) into a sleeve worn on the forearm. The BioSleeve's accompanying algorithms can reliably decode as many as sixteen discrete hand gestures and estimate the continuous orientation of the forearm. These gestures and positions are mapped to robot commands that, to varying degrees, integrate with the robot's perception of its environment and its ability to complete tasks autonomously. This flexible approach enables, for example, supervisory point-to-goal commands, virtual joystick for guarded teleoperation, and high degree of freedom mimicked manipulation, all from a single device. The BioSleeve is meant for portable field use; unlike other gesture recognition systems, use of the BioSleeve for robot control is invariant to lighting conditions, occlusions, and the human-robot spatial relationship and does not encumber the user's hands. The BioSleeve control approach has been implemented on three robot types, and we present proof-of-principle demonstrations with mobile ground robots, manipulation robots, and prosthetic hands.

We investigate the applicability of an evolvable hardware classifier architecture for electromyography (EMG) data from the BioSleeve wearable human-machine interface, with the goal of having embedded training and classification. We investigate classification accuracy for datasets with 17 and 11 gestures and compare to results of Support Vector Machines (SVM) and Random Forest classifiers. Classification accuracies are 91.5% for 17 gestures and 94.4% for 11 gestures. Initial results for a field programmable array (FPGA) implementation of the classifier architecture are reported, showing that the classifier architecture fits in a Xilinx XC6SLX45 FPGA. We also investigate a bagging-inspired approach for training the individual components of the classifier with a subset of the full training data. While showing some improvement in classification accuracy, it also proves useful for reducing the number of training instances and thus reducing the training time for the classifier.

This paper describes a high fidelity mission concept systems testbed at JPL, called Lunar Surface Operations Testbed (LSOT). LSOT provides a unique infrastructure that enables mission concept studies designers to configure and demonstrate end-to-end surface operations using existing JPL mission operations and ground support tools, Lander, robotic arm, stereo cameras, flight software, and soil simulant (regolith), in a high fidelity functional testbed. This paper will describe how LSOT was used to support the MoonRise mission concept study. MoonRise: Lunar South Pole-Aitken Basin Sample Return Mission would place a lander in a broad basin near the moon's South Pole and return approximately two pounds of lunar materials to Earth for study. MoonRise was one of three candidate missions competing to be selected as the third mission for NASA's New Frontiers Program of Solar System Explorations. LSOT was used to demonstrate JPL's extensive experience and understanding of the MoonRise Lander capabilities, design maturity, surface operations systems engineering issues, risks and challenges.

We present a model of cerebellar cortex that combines two types of learning: feedforward predictive association based on local Hebbian-type learning between granule cell ascending branch and parallel fiber inputs, and reinforcement learning with feedback error correction based on climbing fiber activity. The model is motivated by recent physiological and anatomical evidence and has more computational capacity than previous functional models of cerebellum. To demonstrate the model's utility, we simulated the control of a simple virtual arm. The model successfully learned to control the timing of release for the arm during a target-throwing task. (C) 2002 Elsevier Science B.V. All rights reserved.

We present a simulation of the electrosensory input of the weakly electric fish Apteronotus leptorhynchus.This fish senses its environment by producing a sinusoidal voltage difference between its body and tail sections, causing an electric field and a current distribution in the surrounding water.If an object is nearby which has different electrical conductivity from the surrounding water, the current distribution is disturbed on the skin of the fish.The fish senses this difference from the usual current distribution, and infers the presence and location of the object.