Autonomous systems performing object manipulation in human-robot collaboration scenarios face fundamental challenges in balancing adaptability with safety constraints. We present a RL framework that addresses these challenges through safety-aware policy learning. Building upon OpenAI Safety Gym, we extend its capabilities by implementing a robotic arm model for object manipulation tasks. Our approach employs end-to-end policy learning, comparing a constrained Lagrangian variant of Proximal Policy Optimization (cPPO) against standard PPO and Soft Actor-Critic (SAC) baselines. To handle high-dimensional 1 visual inputs, we develop a structured representation learning method that effectively captures multiple skills, objects, and their interactions. The framework enables goal-conditioned manipulation across object configurations, demonstrating strong compositional generalization: the agent trained on simple two-cubic object scenarios successfully generalized to tasks with three distinct objects in more cluttered settings. Due to computational constraints of high-mass objects in the simulation environment, testing was limited to scenarios with up to three objects. Experimental results show that cPPO achieves superior safety performance with an average episode cost of 15.26 compared to 18.03 for PPO and 19.48 for SAC. While cPPO’s task performance (average episode reward ∼30) is slightly lower than PPO’s (∼35), it significantly outperforms SAC (∼12). The algorithms demonstrate convergence by 200,000 environment steps, with cPPO achieving rapid safety compliance while exhibiting steady convergence in learning performance. These findings demonstrate the effectiveness of integrating safety constraints within RL for autonomous manipulation, advancing the practical deployment of collaborative robotic systems.

The deformation behavior of polymers is influenced not only by service conditions such as temperature and the strain rate but also significantly by the formation process. However, existing simulation frameworks typically treat injection molding and the in-service mechanical response separately, making it difficult to capture the impact of the thermal history on large deformation behavior. In this study, the deformation behavior of injection-molded polycarbonate (PC) was investigated by accounting for its thermal history during formation, achieved through combined experimental characterization and constitutive modeling. PC specimens were prepared via injection molding followed by annealing at different molding/annealing temperatures and durations. Uniaxial tensile tests were conducted using a Zwick universal testing machine at strain rates of 10⁻³–10⁻¹ s⁻¹ and temperatures ranging from 293 K to 353 K to obtain stress–strain curves. The effects of the strain rate, testing temperature, and annealing conditions were thoroughly examined. Building upon a previously proposed phenomenological model, a new constitutive framework incorporating thermal history effects during formation was developed to characterize the large deformation behavior of PC. This model was implemented in ABAQUS/Explicit using a user-defined material subroutine. Predicted stress–strain curves exhibit excellent agreement with the experimental data, accurately reproducing elastic behavior, yield phenomena, and strain-softening and strain-hardening stages.