Maani Ghaffari

This work presents GINIO, a geometric SO(3)-equivariant interface for neural inertial odometry under arbitrary rotations of the IMU measurement frame, and introduces Last-Frame Alignment (LFA), a deterministic preprocessing step that is provably equivalent to world-frame training for SO(3)-equivariant predictors.

In-vivo and ex-vivo experiments validate that LapaTrack-3D provides robust 3D tracking and effectively handles typical challenges such as poor illumination, fast motion, out-of-field-of-view scenarios, partial visibility, and ``organ-background''relative motion.

Cyclops enables LiDAR to produce high-quality RGB video, outperforming traditional cameras in low-light scenarios and revolutionizing robotic perception.

Current navigation agents falter in cross-context scenarios, with a significant performance drop when moving from outdoor to indoor-to-outdoor environments.

DeepCORD adapts solver parameters in real-time, outperforming traditional methods in distributed optimization across complex geometric scenarios.

Rigid body trajectory optimization can now avoid singularities and achieve faster convergence with a new structure-aware method that respects the underlying geometry.

LLMs can navigate more efficiently in unfamiliar environments by reasoning over a tree of possible paths, not just isolated waypoints, enabling them to consider en-route information gain and prune unpromising branches.

Forget pre-built maps: this new navigation agent interprets signs like a human, achieving 80% success in complex indoor environments.

Exploiting symmetry in tensegrity robot design slashes training data needs by 80% while boosting contact estimation accuracy by 15%, all with a simple graph neural network.