Autonomous self-burying seed carriers for aerial seeding.

Aerial seeding can quickly cover large and physically inaccessible areas1 to improve soil quality and scavenge residual nitrogen in agriculture2, and for postfire reforestation3-5 and wildland restoration6,7. However, it suffers from low germination rates, due to the direct exposure of unburied seeds to harsh sunlight, wind and granivorous birds, as well as undesirable air humidity and temperature1,8,9. Here, inspired by Erodium seeds10-14, we design and fabricate self-drilling seed carriers, turning wood veneer into highly stiff (about 4.9 GPa when dry, and about 1.3 GPa when wet) and hygromorphic bending or coiling actuators with an extremely large bending curvature (1,854 m-1), 45 times larger than the values in the literature15-18. Our three-tailed carrier has an 80% drilling success rate on flat land after two triggering cycles, due to the beneficial resting angle (25°-30°) of its tail anchoring, whereas the natural Erodium seed's success rate is 0%. Our carriers can carry payloads of various sizes and contents including biofertilizers and plant seeds as large as those of whitebark pine, which are about 11 mm in length and about 72 mg. We compare data from experiments and numerical simulation to elucidate the curvature transformation and actuation mechanisms to guide the design and optimization of the seed carriers. Our system will improve the effectiveness of aerial seeding to relieve agricultural and environmental stresses, and has potential applications in energy harvesting, soft robotics and sustainable buildings.

Mapless mobile robot navigation at the edge using self-supervised cognitive map learners.

Navigation of mobile agents in unknown, unmapped environments is a critical task for achieving general autonomy. Recent advancements in combining Reinforcement Learning with Deep Neural Networks have shown promising results in addressing this challenge. However, the inherent complexity of these approaches, characterized by multi-layer networks and intricate reward objectives, limits their autonomy, increases memory footprint, and complicates adaptation to energy-efficient edge hardware. To overcome these challenges, we propose a brain-inspired method that employs a shallow architecture trained by a local learning rule for self-supervised navigation in uncharted environments. Our approach achieves performance comparable to a state-of-the-art Deep Q Network (DQN) method with respect to goal-reaching accuracy and path length, with a similar (slightly lower) number of parameters, operations, and training iterations. Notably, our self-supervised approach combines novelty-based and random walks to alleviate the need for objective reward definition and enhance agent autonomy. At the same time, the shallow architecture and local learning rule do not call for error backpropagation, decreasing the memory overhead and enabling implementation on edge neuromorphic processors. These results contribute to the potential of embodied neuromorphic agents utilizing minimal resources while effectively handling variability.