Parallel scheduling of task graphs has been an important research topic in the field of parallel processing, and it is well known to be a challenging NP-complete problem. Scheduling in data flow systems can be represented by a directed acyclic graph (DAG). In parallel task scheduling using DAG, managing the dependent tasks reduce overall execution time. However, the algorithm cannot be applied to real-time systems with a mix of different deadlines and multi outputs, such as an autonomous driving system, because real-time systems can be represented by a DAG are mainly limited threads known as a fork-join structure. Real-time scheduling algorithm that does not depend on the structure of DAG can be widely used. This paper presents the Heterogeneous Laxity-Based Scheduling (HLBS) algorithm, which uses list scheduling heuristics to solve this problem. HLBS computes the rest time until deadlines, known as laxity, and preferentially assigns a task with shorter laxity to the processor. This enables scheduling of multiple deadlines to reduce deadline miss rate. The evaluation results demonstrate that HLBS reduced the deadline miss rate by an average of 45.6 % while achieving a performance level comparable to that of algorithms presented in previous studies.