Sai Haneesh Allu

Ninad Khargonkar, Sai Haneesh Allu, Yangxiao Lu et al.

We present a new reproducible benchmark for evaluating robot manipulation in the real world, specifically focusing on pick-and-place. Our benchmark uses the YCB objects, a commonly used dataset in the robotics community, to ensure that our results are comparable to other studies. Additionally, the benchmark is designed to be easily reproducible in the real world, making it accessible to researchers and practitioners. We also provide our experimental results and analyzes for model-based and model-free 6D robotic grasping on the benchmark, where representative algorithms are evaluated for object perception, grasping planning, and motion planning. We believe that our benchmark will be a valuable tool for advancing the field of robot manipulation. By providing a standardized evaluation framework, researchers can more easily compare different techniques and algorithms, leading to faster progress in developing robot manipulation methods.

Qifan Zhang, Sai Haneesh Allu, Jikai Wang et al.

Detecting and segmenting novel object instances in open-world environments is a fundamental problem in robotic perception. Given only a small set of template images, a robot must locate and segment a specific object instance in a cluttered, previously unseen scene. Existing proposal-based approaches are highly sensitive to proposal quality and often fail under occlusion and background clutter. We propose L2G-Det, a local-to-global instance detection framework that bypasses explicit object proposals by leveraging dense patch-level matching between templates and the query image. Locally matched patches generate candidate points, which are refined through a candidate selection module to suppress false positives. The filtered points are then used to prompt an augmented Segment Anything Model (SAM) with instance-specific object tokens, enabling reliable reconstruction of complete instance masks. Experiments demonstrate improved performance over proposal-based methods in challenging open-world settings.

Sai Haneesh Allu, Itay Kadosh, Tyler Summers et al.

We present a modular robotic system for autonomous exploration and semantic updating of large-scale unknown environments. Our approach enables a mobile robot to build, revisit, and update a hybrid semantic map that integrates a 2D occupancy grid for geometry with a topological graph for object semantics. Unlike prior methods that rely on manual teleoperation or precollected datasets, our two-phase approach achieves end-to-end autonomy: first, a modified frontier-based exploration algorithm with dynamic search windows constructs a geometric map; second, using a greedy trajectory planner, environments are revisited, and object semantics are updated using open-vocabulary object detection and segmentation. This modular system, compatible with any metric SLAM framework, supports continuous operation by efficiently updating the semantic graph to reflect short-term and long-term changes such as object relocation, removal, or addition. We validate the approach on a Fetch robot in real-world indoor environments of approximately $8,500$m$^2$ and $117$m$^2$, demonstrating robust and scalable semantic mapping and continuous adaptation, marking a fully autonomous integration of exploration, mapping, and semantic updating on a physical robot.

Yu Xiang, Sai Haneesh Allu, Rohith Peddi et al.

We introduce a new trajectory optimization method for robotic grasping based on a point-cloud representation of robots and task spaces. In our method, robots are represented by 3D points on their link surfaces. The task space of a robot is represented by a point cloud that can be obtained from depth sensors. Using the point-cloud representation, goal reaching in grasping can be formulated as point matching, while collision avoidance can be efficiently achieved by querying the signed distance values of the robot points in the signed distance field of the scene points. Consequently, a constrained nonlinear optimization problem is formulated to solve the joint motion and grasp planning problem. The advantage of our method is that the point-cloud representation is general to be used with any robot in any environment. We demonstrate the effectiveness of our method by performing experiments on a tabletop scene and a shelf scene for grasping with a Fetch mobile manipulator and a Franka Panda arm. The project page is available at \url{https://irvlutd.github.io/GraspTrajOpt}