The timber-harvesting industry is lagging its peer industries, such as mining and agriculture, with respect to deployment of robotic, AI and autonomous technologies. In this paper, we tackle automation of a critical task that arises in transporting logs from the forest to the sawmill: the log loading operation. This work is motivated by the acute shortages of human operators and the need to improve the efficiencies of timber-harvesting processes. To this end, we demonstrate the full autonomy pipeline for the log loading operation with a fixed-base manipulator (a.k.a., the crane), starting with perception of logs around the machine, then grasp planning for where to grasp logs, through motion planning and control of the log loading maneuver. Our main contribution is in the full integration of the necessary elements to achieve a completely autonomous loading cycle, where the crane picks up and loads all logs within its reach on a trailer. Notable features of our implementation are a generalizable perception stack, a grasp planner to pick up multiple logs at a time and an extensive experimental campaign conducted outdoors, on a commercial log loader retrofitted for autonomy. Our results demonstrate an overall 87% success rate of the log loading operation, with primary failure cases due to log segmentation errors and deficiencies in the final height adjustment algorithm for grasping logs. We also present detailed timing results of the main parts of the autonomy pipeline, which support the feasibility of deployment in operational environment.

In automatic bioacoustic monitoring it is important to do continuous observations to capture rare events, but storage and communication overheads typically prevent continuous real-time monitoring. To overcome this limitation, this paper presents a low complexity local processing method for acoustic signals targeting resource constrained nodes and preprocessing and segmentation techniques in line with the proposed local processing technique for effective and continuous identification of bird calls. This paper also focuses on designing of overall automatic bioacoustic monitoring system including feature extraction and classification. The proposed system with Two-windows method shows maximum accuracy of 93.85% when trained and tested using SVM classifier with 214 real world recordings containing calls of 5 bird species. Having local processing at node level has shown 43% reduction of space requirement at node level and 24% reduction of processing time.