Open Access

This work aims to increase the energy efficiency of a delta kinematic robot using reinforcement learning (RL) by examining and optimizing the robot's movement sequences between variable positions. An RL environment was developed to train a model that is able to automatically generate an energy efficient trajectory between two random points in a 3D-workspace, while avoiding a static cubic obstacle with random position and size. Using a digital twin, the robot's limits and energy consumption were simulated during training. By balancing the reward function between the task of reaching the goal and minimizing energy consumption, a final AI model was created that generates trajectories using around 28% less energy than manually created ones.

Climate change and forest degradation have created an urgent reforestation crisis in Germany, with current estimates indicating over 525,000 [1] hectares requiring restoration. Drone-based seed dispersal systems exist commercially but suffer from challenges such as low germination rate [2] and random seedling distribution. Container seedling planting can achieve success rates exceeding 90% [3] but requires complex soil preparation and precise planting methodology. The DraAuf project (Drohnen-gestützte automatisierte Aufforstung) [4], funded by the German Federal Ministry for Environment as part of the KILeuchttürme initiative, addresses this challenge by developing an autonomous UAV-deployed planting robot. This paper systematically investigates impact drilling strategies optimized for the extreme constraints of aerial deployment.

The agricultural sector increasingly relies on autonomous systems that operate in complex and variable environments. Unlike on-road applications, agricultural automation integrates driving and working processes, each of which imposes distinct operational constraints. Handling this complexity and ensuring consistency throughout the development and validation processes requires a structured, transparent, and verified description of the environment. However, existing Operational Design Domain (ODD) concepts do not yet address the unique challenges of agricultural applications. Therefore, this work introduces the Agricultural ODD (Ag-ODD) Framework, which can be used to describe and verify the operational boundaries of autonomous agricultural systems. The Ag-ODD Framework consists of three core elements. First, the Ag-ODD description concept, which provides a structured method for unambiguously defining environmental and operational parameters using concepts from ASAM Open ODD and CityGML. Second, the 7-Layer Model derived from the PEGASUS 6-Layer Model, has been extended to include a process layer to capture dynamic agricultural operations. Third, the iterative verification process verifies the Ag-ODD against its corresponding logical scenarios, derived from the 7-Layer Model, to ensure the Ag-ODD’s completeness and consistency. Together, these elements provide a consistent approach for creating unambiguous and verifiable Ag-ODD. Demonstrative use cases show how the Ag-ODD Framework can support the standardization and scalability of environmental descriptions for autonomous agricultural systems.

Robots are often showcased as precise machines that seamlessly collaborate with humans. However, reality diverges significantly, as robots encounter failures that lead to suboptimum outcomes, misunderstandings and socially awkward situations. Conversely, human-induced errors in these interactions often go undetected by robots, amplifying the complexity of the interaction dynamics on top of the uncertainties in the environment and interaction contexts. In human-robot interaction (HRI) research, errors–wrong actions that are made due to the lack of knowledge–and mistakes–actions that turn out to be wrong–are commonly viewed as impediments to achieving flawless collaboration. Scholars and practitioners aspire to meticulously control variables, creating environments with predictable storylines and outcomes. Nevertheless, the controlled setting of a laboratory rarely mirrors the unpredictable nature of real-world scenarios, contributing to a notable disparity between expectations and actual experiences. The ability of robots to navigate erroneous situations is paramount to the sustained success of HRI. These imperfections are also perfect learning opportunities for robots to continuously adapt to the ever-shifting complexity and dynamics in real-world HRI. This Research Topic contains research that addresses the gap between anticipated perfection and the inherent uncertainties in a diverse range of real-world applications. The papers presented here shine light on a variety of aspects ranging from novel technical approaches to repair failures in HRI, to user studies that aim to understand social dimensions of errors in HRI.

Despite the wide body of literature on motion planning for autonomous robots targeting structured agricultural environments, there remains a need for more efficient and reliable approaches for unstructured terrains. This work is motivated by a cooperation with the startup Paltech, which develops a weed-removal robot for grasslands. In this work, we employ a typical layered approach for robot navigation. However, in contrast to standard navigation tasks, such as point-to-point navigation, the global planner must solve the more challenging problem of visiting multiple targets in an optimal way while considering the kinematic constraints of the vehicle.