Researchers are increasingly focused on enabling groups of multiple unmanned vehicles to operate cohesively in complex, real-world environments, where coordinated formation control and obstacle avoidance are essential for executing sophisticated collective tasks. This paper presents a Distributed Formation Control and Obstacle Avoidance (DFCOA) framework for multi-unmanned ground vehicles (UGV). DFCOA integrates a virtual leader structure for global guidance, an improved A* path planning algorithm with an advanced cost function for efficient path planning, and a repulsive-force- based improved vector field histogram star(VFH*) technique for collision avoidance. The virtual leader generates a reference trajectory while enabling distributed execution; the improved A* algorithm reduces planning time and number of nodes to determine the shortest path from the starting position to the goal; and the improved VFH* uses 2D LiDAR data with inter-agent repulsive force to simultaneously avoid collision with obstacles and maintain safe inter-vehicle distances. The formation stability of the proposed DFCOA reaches 95.8% and 94.6% in two scenarios, with root mean square(RMS) centroid errors of 0.9516 and 1.0008 m, respectively. Velocity tracking is precise (velocity centroid error RMS of 0.2699 and 0.1700 m/s), and linear velocities closely match the desired 0.3 m/s. Safety metrics showed average collision risks of 0.7773 and 0.5143, with minimum inter-vehicle distances of 0.4702 and 0.8763 m, confirming collision-free navigation of four UGVs. DFCOA outperforms conventional methods in formation stability, path efficiency, and scalability, proving its suitability for decentralized multi-UGV applications.