Search results

The choice of crops to produce at a location depends to a large degree on the climate. As the climate changes and food demand evolves, farmers may need to produce a different mix of crops. This study assesses how much cropland may be subject to such upheavals at the global scale, and then focuses on China as a case study to examine how spatial heterogeneity informs different contexts for adaptation within a country.

A global agricultural economic model is linked to a cropland allocation algorithm to generate maps of cropland distribution under historical and future conditions. The mix of crops at each location is examined to determine whether it is likely to experience a major shift.

Two-thirds of rainfed cropland and half of irrigated cropland are likely to experience substantial upheaval of some kind.

This analysis helps establish a global context for the local changes that producers might face under future climate and socioeconomic changes. The scale of the challenge means that the agricultural sector needs to prepare for these widespread and diverse upheavals.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.