Motion planning in dynamic environments using context-aware human trajectory prediction

Finean, Mark Nicholas; Petrović, Luka; Merkt, Wolfgang; Marković, Ivan; Havoutis, Ioannis

doi:10.1016/j.robot.2023.104450

Cited by 8 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Equation (10), the action space of the agent is the end of the robotic arm in the x, y, and z directions. The state of the end of the robotic arm is shown in the equation [30].…”

Section: State Space and Action Spacementioning

confidence: 99%

“…The fast progress of deep learning and computing power has made deep reinforcement learning a reality, and it has been gradually used in games, robot navigation, industrial production, and other fields [10]. Although deep reinforcement learning algorithms can achieve certain results in simple dynamic environments, when the environment is complex, the algorithm's perception of the environment is weakened, resulting in reduced performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robotic Manipulator in Dynamic Environment with SAC Combing Attention Mechanism and LSTM

Kuang,

Zhou

2024

Electronics

View full text Add to dashboard Cite

The motion planning task of the manipulator in a dynamic environment is relatively complex. This paper uses the improved Soft Actor Critic Algorithm (SAC) with the maximum entropy advantage as the benchmark algorithm to implement the motion planning of the manipulator. In order to solve the problem of insufficient robustness in dynamic environments and difficulty in adapting to environmental changes, it is proposed to combine Euclidean distance and distance difference to improve the accuracy of approaching the target. In addition, in order to solve the problem of non-stability and uncertainty of the input state in the dynamic environment, which leads to the inability to fully express the state information, we propose an attention network fused with Long Short-Term Memory (LSTM) to improve the SAC algorithm. We conducted simulation experiments and present the experimental results. The results prove that the use of fused neural network functions improved the success rate of approaching the target and improved the SAC algorithm at the same time, which improved the convergence speed, success rate, and avoidance capabilities of the algorithm.

show abstract

“…In Equation (10), the action space of the agent is the end of the robotic arm in the x, y, and z directions. The state of the end of the robotic arm is shown in the equation [30].…”

Section: State Space and Action Spacementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%