arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.27632cs.ROcs.AIcs.CV
收藏

ContraMap:基于对比学习的机器人环境表示不确定性映射

ContraMap: Contrastive Uncertainty Mapping for Robot Environment Representation

School of Computer Science and the Australian Centre for Robotics, University of Sydney(悉尼大学计算机科学学院与澳大利亚机器人中心)

Chi Cuong Le, Weiming Zhi

AI总结:

ContraMap通过对比学习方法,结合核基判别图和显式不确定性类,实现实时环境预测与空间不确定性估计,优于贝叶斯核图基线。

摘要:

可靠的机器人感知不仅需要预测场景结构,还需识别预测不可靠的区域。我们提出了ContraMap,一种对比连续映射方法,通过合成噪声样本训练的显式不确定性类增强核基判别图。该方法将未观测区域视为对比类,实现实时环境预测与空间不确定性估计,无需贝叶斯推断。在简单混合模型视图下,我们展示出不确定性类的概率是距离感知不确定性代理的单调函数。在2D占用映射、3D语义映射和桌面上场景重建实验中,ContraMap保持了映射质量,产生空间一致的不确定性估计,并显著优于贝叶斯核图基线。

英文摘要:

Reliable robot perception requires not only predicting scene structure, but also identifying where predictions should be treated as unreliable due to sparse or missing observations. We present ContraMap, a contrastive continuous mapping method that augments kernel-based discriminative maps with an explicit uncertainty class trained using synthetic noise samples. This formulation treats unobserved regions as a contrastive class, enabling joint environment prediction and spatial uncertainty estimation in real time without Bayesian inference. Under a simple mixture-model view, we show that the probability assigned to the uncertainty class is a monotonic function of a distance-aware uncertainty surrogate. Experiments in 2D occupancy mapping, 3D semantic mapping, and tabletop scene reconstruction show that ContraMap preserves mapping quality, produces spatially coherent uncertainty estimates, and is substantially more efficient than Bayesian kernelmap baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑