Tier-scalable reconnaissance: the future in autonomous C4ISR systems has arrived: progress towards an outdoor testbed

Abstract

Autonomous reconnaissance missions are called for in extreme environments, as well as in potentially hazardous (e.g., the theatre, disaster-stricken areas, etc.) or inaccessible operational areas (e.g., planetary surfaces, space). Such future missions will require increasing degrees of operational autonomy, especially when following up on transient events. Operational autonomy encompasses: (1) Automatic characterization of operational areas from different vantages (i.e., spaceborne, airborne, surface, subsurface); (2) automatic sensor deployment and data gathering; (3) automatic feature extraction including anomaly detection and region-of-interest identification; (4) automatic target prediction and prioritization; (5) and subsequent automatic (re-)deployment and navigation of robotic agents. This paper reports on progress towards several aspects of autonomous C 4 ISR systems, including: Caltech-patented and NASA award-winning multi-tiered mission paradigm, robotic platform development (air, ground, water-based), robotic behavior motifs as the building blocks for autonomous telecommanding, and autonomous decision making based on a Caltech-patented framework comprising sensor-data-fusion (feature-vectors), anomaly detection (clustering and principal component analysis), and target prioritization (hypothetical probing).

An adaptive hierarchical approach to lidar-based autonomous robotic navigation

“…Multi-tiered robotic exploration architectures will not only introduce mission redundancy, safety, and robustness, but will also enable intelligent, objective-driven, and distributed reconnaissance in real time, thus providing responsiveness to transient events. As reported before 8 , such systems and missions require increasing degrees of operational autonomy, comprising at least the following requirements: (1) automatic characterization of operational areas from different vantages, (2) automatic sensor deployment and data gathering, (3) automatic feature extraction, anomaly detection, and region-ofinterest or target identification, (4) automatic region-of-interest or target prioritization, and (5) subsequent automatic redeployment and navigation of robotic agents to regions or targets of interest. The potential for autonomous exploration (i.e., in the absence of human control) inherent to multi-tiered robotic exploration architectures lies predominantly in the constructive integration of various vantage points (e.g., space, air, ground, sub-surface) and the resulting autonomous telecommanding capabilities, especially in hierarchical mission architectures, such as Tier-Scalable Reconnaissance.…”

“…2), robotic sea surface vehicles (i.e., sea rovers), and robotic unmanned aerial vehicles (i.e., air rovers). These robotic agents and their respective specifications and capabilities have been described in detail in [8][9][10]. In the following we briefly rehash the specifications of the land rovers used to devise, study, and validate the autonomous robotic navigation algorithms.…”

“…Ultimately, we will interface the Automated Global Feature Analyzer TM (AGFA TM ) 11,8,[12][13][14][15] with the robotic multi-agent testbed (Section 2) for TSR operations. The AGFA TM software framework is a first step towards objective scene description, unbiased anomaly detection (i.e., based on feature-spaces alone), and target prioritization in unknown environments (e.g., planetary surfaces & sub-surfaces).…”

“…Autonomous multi-tiered robotic exploration architectures, such as Tier-Scalable Reconnaissance (TSR) [1][2][3][4][5][6][7][8] ( Fig. 1), will be essential to meet the needs of fully autonomous C 4 ISR systems for Earth-bound applications (both military and civilian) and upcoming fully autonomous space missions necessary to explore planetary bodies beyond the Moon and Mars, such as Enceladus, Titan, Europa, Venus, and asteroids (e.g., for mining purposes), etc.…”

Paths to non-deterministic autonomy: practical and qualitative considerations towards a Hawking-Musk-esque nightmare

“…o Multi-objective path/traverse planning and optimization; [14][15][16] o Maximized exploration, e.g., deepest path exploration; 3 o Autonomous tele-commanding of robotic agents towards target areas or to avoid obstacles; [16][17][18][19][20][21][22][23][24][25] o Autonomous robotic agent redeployment/reconfiguration; [18][19][20][21][22][23][24][25] • Answer (science) questions, e.g., through detection/identification of (feature-based) anomalies and/or regions of interest, such as, but not limited to, heat sources, locales of methane outgassing, subsurface water ice deposits, etc. [26][27][28]5,6 o Autonomous characterization of and anomaly detection in an operational area; 26,27,5,6 o Autonomous target prioritization; 28 o Autonomous robotic limb/actuator deployment towards target areas, e.g., for sampling or probing.…”