Autonomous pilot is crucial in integrally promoting the autonomy of an unmanned surface vehicle (USV). However, the integration mechanism of decision and control is still unclear within the entire autonomy. In this paper, by organically bridging path planning and tracking, an autonomous pilot framework with waypoints generation, path smoothing and policy guidance of a USV in congested waters is established, for the first time. Incorporating elite and diversity operations into the genetic algorithm (GA), an elite-duplication GA (EGA) strategy is devised to optimally generate sparse waypoints in a constrained space. The B-spline technique is further deployed to make flexibly smooth interpolation facilitating path smoothing supported by optimal sparse-waypoints. Seamlessly bridged by the parametric smooth path, deep reinforcement learning (DRL) technique is resorted to continuously extract in-depth pilotage policies, i.e., mappings from path tracking errors, collision risks and control constraints to continuous control forces/torques. Eventually, the entire spline-bridged EGA-DRL (SED) framework merits autonomous global-pilotage and local-reaction in an organically modular manner. Comprehensive validations and comparisons in various real-world geographies demonstrate the effectiveness and superiority of the proposed SED autonomous pilot framework.

Autonomous Pilot of Unmanned Surface Vehicles: Bridging Path Planning and Tracking

Uninterrupted path planning system for Multi-USV sampling mission in a cluttered ocean environment

USV path planning method with velocity variation and global optimisation based on AIS service platform

Swarm robots in mechanized agricultural operations: A review about challenges for research

The path planning issue of the underactuated autonomous underwater vehicle (AUV) under ocean current disturbance is studied in this paper. In order to improve the AUV’s path planning capability in the unknown environments, a deep reinforcement learning (DRL) path planning method based on double deep Q Network (DDQN) is proposed. It is created from an improved convolutional neural network, which has two input layers to adapt to the processing of high-dimensional environments. Considering the maneuverability of underactuated AUV under current disturbance, especially, the issue of ocean current disturbance under unknown environments, a dynamic and composite reward function is developed to enable the AUV to reach the destination with obstacle avoidance. Finally, the path planning ability of the proposed method in the unknown environments is validated by simulation analysis and comparison studies.

Path Planning Based on Deep Reinforcement Learning for Autonomous Underwater Vehicles Under Ocean Current Disturbance

Global path planning and multi-objective path control for unmanned surface vehicle based on modified particle swarm optimization (PSO) algorithm

Protected areas are considered the cornerstone of endangered wildlife conservation. However, quantified conservation potentials and limitations of large carnivores in protected areas are lacking. In the Northeast Tiger and Leopard National Park (NTLNP) in China, our camera trap survey in 2019 found 26–27 adult Amur tigers and 49–59 adult Amur leopards occurring in the park. Based on spatial area, current prey populations, and environmental carrying capacity of prey, we estimated the supportable number of tigers to be 55, 90, and 101 individuals, respectively. For leopard, these values were 95, 356, and 572, respectively. Further simulations indicated that human land use change scenarios did not contribute much to increasing the potential prey‐supportable populations of Amur tiger and leopard. Our results showed that the number of tigers and leopards in NTLNP is currently low and has a high recovery potential. However, even the highest supportable population is not enough to support the sustainable existence of an Amur tiger population. Therefore, we suggest that, in addition to further restoration and improvement of the prey population and habitat quality in NTLNP, managers should strengthen the connectivity between NTLNP and other habitat patches to form a well‐connected network of protected areas. Promoting the spread of tigers and leopards outwards from this source population in NTLNP through ecological corridor construction would enlarge the area of habitat and is a crucial measure for realizing the sustainable survival of an Amur tiger population in Northeast China.

Conservation potentials and limitations of large carnivores in protected areas: A case study in Northeast China

Hamenya Mpemba1, Fan Yang 1, Kirsty J. MacLeod2,3, Dusu Wen1, Yan Liu1,4 and Guangshun Jiang1,* 1Feline Research Center of National Forestry and Grassland Administration, College of Wildlife and Protected Area, Northeast Forestry University, 26 Hexing Road, Harbin, Heilongjiang 150040, P.R. China 2Department of Ecosystem Science and Management, Pennsylvania National University, Forest Resources Building, University Park, PA 16802, USA 3Department of Biology, Lund University, Sölvegatan 37, 223 62 Lund, Sweden 4General Station for Surveillance of Wildlife-Borne Infectious Diseases, State Forestry and Grassland Administration, Shenyang, Liaoning Province, 110034, PR China

Influences of Predator Cues on the Incidence of Ungulates, Mesopredators and Top Predators in the Greater Khingan Mountains, Northeastern China

Habitat selection and daily activity patterns of large herbivores might be affected by inter- and intra-specific interaction, changes of spatial scale, and seasonal temperature. To reveal what factors were driving the habitat selection of moose, we collected moose (Alces alces) and roe deer (Capreolus pygargus bedfordi) occurrence data, analyzed the multi-scale habitat selection and daily activity patterns of moose, and quantified the effects of spatial heterogeneity distribution of temperature, as well as the occurrence of roe deer on these habitat selection processes. Our results suggested that moose and roe deer distribution spatially overlap and that moose habitat selection is especially sensitive to landscape variables at large scales. We also found that the activity patterns of both sexes of moose had a degree of temporal separation with roe deer. In the snow-free season, temperatures drove moose habitat selection to be limited by threshold temperatures of 17 °C; in the snowy season, there were no similar temperature driving patterns, due to the severe cold environment. The daily activity patterns of moose showed seasonal change, and were more active at dawn and nightfall to avoid heat pressure during the snow-free season, but more active in the daytime for cold adaptation to the snow season. Consequently, this study provides new insights on how the comprehensive effects of environmental change and inter- and intra- specific relationships influence the habitat selection and daily activity patterns of moose and other heat sensitive animals with global warming.

/pdf/effects-of-inter-and-intra-specific-interactions-on-moose-kzt9vwks.pdf

Effects of Inter- and Intra-Specific Interactions on Moose Habitat Selection Limited by Temperature

Global warming is deeply influencing various ecological processes, especially regarding the phenological synchronization pattern between species, but more cases around the world are needed to reveal it. We report how the forest leaf phenology and ungulate molting respond differently to climate change, and investigate whether it will result in a potential phenology mismatch. Here, we explored how climate change might alter phenological synchronization between forest leaf phenology and Siberian roe deer (Capreolus pygargus) molting in northeast China based on a camera-trapping dataset of seven consecutive years, analyzing forest leaf phenology in combination with records of Siberian roe deer molting over the same period by means of wavelet analysis. We found that the start of the growing season of forest leaf phenology was advanced, while the end of the growing season was delayed, so that the length of the growing season was prolonged. Meanwhile, the start and the end of the molting of Siberian roe deer were both advanced in spring, but in autumn, the start of molting was delayed while the end of molting was advanced. The results of wavelet analysis also suggested the time lag of synchronization fluctuated slightly from year to year between forest leaf phenology and Siberian roe deer molting, with a potential phenology mismatch in spring, indicating the effect of global warming on SRD to forest leaf phenology. Overall, our study provides new insight into the synchronization between forest leaf phenology and ungulate molting, and demonstrates feasible approaches to data collection and analysis using camera-trapping data to explore global warming issues.

/pdf/wavelet-analysis-reveals-phenology-mismatch-between-leaf-2icv8xfd.pdf

Dusu Wen

Papers

Global path planning and multi-objective path control for unmanned surface vehicle based on modified particle swarm optimization (PSO) algorithm

Conservation potentials and limitations of large carnivores in protected areas: A case study in Northeast China

Influences of Predator Cues on the Incidence of Ungulates, Mesopredators and Top Predators in the Greater Khingan Mountains, Northeastern China

Effects of Inter- and Intra-Specific Interactions on Moose Habitat Selection Limited by Temperature

Wavelet Analysis Reveals Phenology Mismatch between Leaf Phenology of Temperate Forest Plants and the Siberian Roe Deer Molting under Global Warming