Shumon Koga

Saida Liu, Nikolay Atanasov, Shumon Koga

This paper proposes MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy, a control policy for active multi-target tracking using a mobile agent. The policy enables multiple behavior modes for the agent, including exploration, tracking, and target reacquisition, without prior knowledge of the target numbers, states, or dynamics. Effective target tracking demands balancing exploration for undetected or lost targets with exploitation, i.e., uncertainty reduction, of detected but uncertain ones. We generate a demonstration dataset from three expert planners including frontier-based exploration, an uncertainty-based hybrid planner switching between frontier-based exploration and RRT* tracking, and a time-based hybrid planner switching between exploration and target reacquisition based on target detection time. Our control policy utilizes a vision transformer for egocentric map tokenization and an attention mechanism to integrate variable target estimates represented by Gaussian densities. Trained as a diffusion model, the policy learns to generate multimodal action sequences through a denoising process. Evaluations demonstrate MATT-Diff's superior tracking performance against other learning-based baselines in novel environments, as well as its multimodal behavior sourced from the multiple expert planners. Our implementation is available at https://github.com/CINAPSLab/MATT-Diff.

Shumon Koga, Miroslav Krstic

This paper considers a safe trajectory tracking of the Stefan problem with a second-order moving boundary dynamics. The model is given by a parabolic Partial Differential Equation (PDE) defined on a time-varying domain of moving boundary governed by a second-order Ordinary Differential Equation (ODE) associated with the Neumann boundary condition. A feedforward control is designed by a series expansion approach to solve the inverse Stefan problem under given reference trajectory of the moving boundary, and the convergence of infinite series is proven. A trajectory tracking controller is derived based on an energy-shaping, which ensures the safety of the model constraint in the closed-loop system. The closed-loop system is also shown to be globally exponentially stable with respect to the tracking error by performing PDE backstepping transformation and Lyapunov analysis. Numerical simulation illustrates an effective tracking performance of the proposed method under a sinusoidal reference trajectory. Code is released at https://github.com/shumon0423/StefanTracking_ACC2026.git.

Pengzhi Yang, Yuhan Liu, Shumon Koga et al.

This paper proposes a method for learning continuous control policies for active landmark localization and exploration using an information-theoretic cost. We consider a mobile robot detecting landmarks within a limited sensing range, and tackle the problem of learning a control policy that maximizes the mutual information between the landmark states and the sensor observations. We employ a Kalman filter to convert the partially observable problem in the landmark state to Markov decision process (MDP), a differentiable field of view to shape the reward, and an attention-based neural network to represent the control policy. The approach is further unified with active volumetric mapping to promote exploration in addition to landmark localization. The performance is demonstrated in several simulated landmark localization tasks in comparison with benchmark methods.

Pengzhi Yang, Shumon Koga, Arash Asgharivaskasi et al.

This paper proposes a novel model-based policy gradient algorithm for tracking dynamic targets using a mobile robot, equipped with an onboard sensor with limited field of view. The task is to obtain a continuous control policy for the mobile robot to collect sensor measurements that reduce uncertainty in the target states, measured by the target distribution entropy. We design a neural network control policy with the robot $SE(3)$ pose and the mean vector and information matrix of the joint target distribution as inputs and attention layers to handle variable numbers of targets. We also derive the gradient of the target entropy with respect to the network parameters explicitly, allowing efficient model-based policy gradient optimization.

Shumon Koga, Arash Asgharivaskasi, Nikolay Atanasov

This paper proposes a novel active Simultaneous Localization and Mapping (SLAM) method with continuous trajectory optimization over a stochastic robot dynamics model. The problem is formalized as a stochastic optimal control over the continuous robot kinematic model to minimize a cost function that involves the covariance matrix of the landmark states. We tackle the problem by separately obtaining an open-loop control sequence subject to deterministic dynamics by iterative Covariance Regulation (iCR) and a closed-loop feedback control under stochastic robot and covariance dynamics by Linear Quadratic Regulator (LQR). The proposed optimization method captures the coupling between localization and mapping in predicting uncertainty evolution and synthesizes highly informative sensing trajectories. We demonstrate its performance in active landmark-based SLAM using relative-position measurements with a limited field of view.

Shumon Koga, Arash Asgharivaskasi, Nikolay Atanasov

This paper develops \emph{iterative Covariance Regulation} (iCR), a novel method for active exploration and mapping for a mobile robot equipped with on-board sensors. The problem is posed as optimal control over the $SE(3)$ pose kinematics of the robot to minimize the differential entropy of the map conditioned the potential sensor observations. We introduce a differentiable field of view formulation, and derive iCR via the gradient descent method to iteratively update an open-loop control sequence in continuous space so that the covariance of the map estimate is minimized. We demonstrate autonomous exploration and uncertainty reduction in simulated occupancy grid environments.