This dissertation proposes an integrated framework for decision-making considering uncertainty in Collaborative Product Design (CPD) environment. The dissertation is divided into three major components as outlined below. First, a bi-level decentralized framework is proposed to model collaborative design problems over autonomous stakeholders with differing objectives. At the system level, a system objective function derived from the Pareto concept is created. A facilitator agent is introduced to search for Pareto optimal solutions based on a Memetic Algorithm (MA). At the design disciplinary level, design agents representing design teams are introduced to optimize their own objectives. The proposed framework will guide the collaborative designs to converge to Pareto optimal solutions given any form of design utility functions. Since the only information exchanged between the two levels is numerical values instead of utility functions, proprietary design information can be protected.;Secondly, two methods for improving Reliability Based Design Optimization (RBDO) are presented. A new approximation approach, termed d-RBDO, is developed to reduce the computational effort of RBDO without scarifying accuracy. Based on the FORM (First Order Reliability Method), the d-RBDO method converts the probabilistic constraints to approximate deterministic constraints so that the RBDO problems can be transformed to deterministic optimization problems. Thus, a regular RBDO problem can be solved by deterministic optimization techniques efficiently without any iterative reliability analysis. In order to address any inaccuracy issues d-RBDO may be susceptible to, a decoupling approach, termed c-RBDO, is proposed to improve the solution quality. Given the solution located at the previous round, the c-RBDO method analyzes its reliability levels. An optimization loop is then performed iteratively over a deterministic optimization problem, where effective deterministic constraints are constructed based on the reliability level of the solution.;Finally, by integrating the d-RBDO and c-RBDO methods with the Memetic Algorithm based decision mechanism, an integrated framework is proposed for CPD under uncertain conditions. The integrated framework converges to Pareto optimal solutions for decentralized design with stochastic variables. Therefore, it enables engineers to make efficient and reliable decisions in CPD environment.