Robot training often takes place in simulated environments, particularly with reinforcement learning. Therefore, multiple training environments are generated using domain randomization to ensure transferability to real-world applications and compensate for unknown real-world states. We propose improving domain randomization by involving human application experts in various stages of the training process. Experts can provide valuable judgments on simulation realism, identify missing properties, and verify robot execution. Our human-in-the-loop workflow describes how they can enhance the process in five stages: validating and improving real-world scans, correcting virtual representations, specifying application-specific object properties, verifying and influencing simulation environment generation, and verifying robot training. We outline examples and highlight research opportunities. Furthermore, we present a case study in which we implemented different prototypes, demonstrating the potential of human experts in the given stages. Our early insights indicate that human input can benefit robot training at different stages.

We present ClaRO, an unsupervised, cluster-based odometry pipeline for 4D imaging radar to improve robustness and reduce long-term drift for radar-only odometry.Our core idea is to utilize density-based clustering to improve ego-motion estimation using per-cluster Doppler-residuals and find a local best result to seed a robust least squares in addition to finding static points for pose estimation. The resulting global inlier mask is used to refine the pose via a weighted iterative closest point (ICP) approach that fuses Doppler and radar cross-section (RCS) cues while down-weighting the radar’s weak elevation axis. The method is fully unsupervised and sensor-agnostic. We compare our method on multiple public datasets (View-of-Delft, HeRCULES, and NTU4DRadLM) and show that our approach provides results that match or exceed recent radar-only odometry baselines (Radar4Motion, EFEAR-4D) and pose graph based 4DRadarSLAM. Our cluster-wise approach significantly reduces long-term drift, achieving a 72.0% improvement in mean absolute trajectory error (ATE) and a 73.2% improvement in absolute rotation error (ARE) compared to state-of-the-art radar odometry methods on the HeRCULES dataset. While remaining competitive in relative pose estimation, our method improves global trajectory consistency and demonstrates robustness across different radar sensors and environments on the VoD and NTU4DRadLM benchmarks.

Detailed digital representations of physical scenes are key in many cases, such as historical site preservation or hazardous area inspection. To automate the capturing process, robots or drones mounted with sensors can algorithmically record the environment from different viewpoints. However, environmental complexities often lead to incomplete captures. We believe humans can support scene capture as their contextual understanding enables easy identification of missing areas and recording errors. Therefore, they need to perceive the recordings and suggest new sensor poses. In this work, we compare two human-centric approaches in Virtual Reality for scene reconstruction through the teleoperation of a remote robot arm, i.e., directly providing sensor poses (direct method) or specifying missing areas in the scans (indirect method). Our results show that directly providing sensor poses leads to higher efficiency and user experience. In future work, we aim to compare the quality of human assistance to automatic approaches.