Consensus-Informed Optimization Over Mixtures for Ambiguity-Aware Object SLAM
This work addresses robust object-level mapping for robots, enabling better planning and manipulation in ambiguous environments, though it is incremental as it builds on existing max-mixtures and iSAM2 frameworks.
The paper tackles the problem of pose ambiguity in object-level SLAM due to symmetry, occlusion, or perceptual failures, proposing a consensus-informed optimization method that improves performance by mitigating local optima in non-convex formulations, as demonstrated on simulated and real datasets.
Building object-level maps can facilitate robot-environment interactions (e.g. planning and manipulation), but objects could often have multiple probable poses when viewed from a single vantage point, due to symmetry, occlusion or perceptual failures. A robust object-level simultaneous localization and mapping (object SLAM) algorithm needs to be aware of this pose ambiguity. We propose to maintain and subsequently disambiguate the multiple pose interpretations to gradually recover a globally consistent world representation. The max-mixtures model is applied to implicitly and efficiently track all pose hypotheses, but the resulting formulation is non-convex, and therefore subject to local optima. To mitigate this problem, temporally consistent hypotheses are extracted, guiding the optimization into the global optimum. This consensus-informed inference method is applied online via landmark variable re-initialization within an incremental SLAM framework, iSAM2, for robust real-time performance. We demonstrate that this approach improves SLAM performance on both simulated and real object SLAM problems with pose ambiguity.