Collaborative autonomous driving with multiple vehicles usually requires the data fusion from multiple modalities. To ensure effective fusion, the data from each individual modality shall maintain a reasonably high quality. However, in collaborative perception, the quality of object detection based on a modality is highly sensitive to the relative pose errors among the agents. It leads to feature misalignment and significantly reduces collaborative performance. To address this issue, we propose RoCo, a novel unsupervised framework to conduct iterative object matching and agent pose adjustment. To the best of our knowledge, our work is the first to model the pose correction problem in collaborative perception as an object matching task, which reliably associates common objects detected by different agents. On top of this, we propose a graph optimization process to adjust the agent poses by minimizing the alignment errors of the associated objects, and the object matching is re-done based on the adjusted agent poses. This process is carried out iteratively until convergence. Experimental study on both simulated and real-world datasets demonstrates that the proposed framework RoCo consistently outperforms existing relevant methods in terms of the collaborative object detection performance, and exhibits highly desired robustness when the pose information of agents is with high-level noise. Ablation studies are also provided to show the impact of its key parameters and components. The code is released at https://github.com/HuangZhe885/RoCo.

Here's something you might not have expected to see Boston Dynamics' robot dog Spot doing any time soon: herding sheep on a rugged New Zealand mountainside. The slightly bizarre sequence is part of a promotional video demonstrating Spot's potential in the agricultural industry; it also includes footage of Spot checking on crops and clambering over rough terrain. The video was put together by robotics software firm Rocos, which is working with Boston Dynamics to explore how its collection of droids can be controlled remotely. The idea is that bots like Spot could be sent out on missions while a human operator sits on the other side of the world. For farmers, that could mean having a robot monitor fields around the clock, checking in on crop growth or fruit ripening, all while being remotely operated.

To prove just how useful Spot, Boston Dynamics' four-legged robot dog, can be, the New Zealand-based robotics company Rocos shared a video of Spot herding sheep across grassy pastures. This is the kind of work Rocos hopes to do as part of a partnership, announced today, with Boston Dynamics. Rocos plans to develop a system that will remotely manage Spot and automate fleets so that they can function independently. In addition to herding sheep, Spot robots might also harvest crops, inspect yields or create real-time maps, Rocos says. These capabilities are all possible now that Spot is more nimble, can handle rugged terrain and can carry infrared and LiDAR cameras.

Northern California weather is pretty temperate. You can get by with a lack of central air conditioning, which is good news since nary a single place I've lived in the Bay Area has had it. But in the summer, there are sweltering days where the heat feels inescapable. While I don't wish I had central air, I do wish I had something better than a box fan for those hottest weeks, something that would follow me around while perfectly streaming air at my dew-drenched face. What I want is a robotic fan.