Resumo: The Robust Interval Distributional Regression (RiDR) model represents a step forward in Symbolic Data Analysis. While traditional regression models often decompose intervals into separate linear regressions for bounds, midpoints, or ranges, the RiDR framework treats intervals as holistic entities by representing them through quantile functions. By assuming a specific distribution within each interval—typically a Uniform distribution—the model accounts for internal variability that is lost in classical point-based summaries. The model imposes non-negativity constraints, which guarantee that the predicted range can never be negative, thus ensuring that the lower bound never exceeds the upper bound. Moreover, to address the sensitivity of standard least-squares methods to atypical data (outliers), the RiDR model integrates robust principles from the Exponential-type kernel robust regression model. Through an iterative re-weighting process, the model identifies and penalizes outliers by assigning them near-zero weights, effectively reducing their influence on parameter estimation in the midpoint and/or range spaces. The combination of distributional theory and robust kernel weighting allows the RiDR model to maintain high precision even in the presence of leverage points, X-space outliers, and Y-space outliers. Furthermore, the model remains highly flexible: it reduces to classical linear regression when applied to degenerate intervals (real numbers) with weights set to one, and it can be adapted to alternative distributions, such as the Symmetric Triangular distribution, making it a versatile tool for complex aggregated datasets. Finally, the RiDR model and other approaches were applied to a real interval-valued dataset, and their performances were compared. The results demonstrated that the RiDR model outperformed the competing models according to different evaluation metrics.