Robotics Vector Processor Architecture for Real-Time Control
This paper proposes a restructurable architecture based on a VLSI Robotics Vector Processor (RVP) chip. It is specially tailored to exploit parallelism in the low-level matrix/vector operations characteristic of the kinematics and dynamics computations required for real-time control. The RVP is comprised of three tightly synchronized 32-bit floating-point processors to provide adequate computational power. Besides adder and multiplier units in each processor, the RVP contains a triple register-file, dual shift network and dual high-speed input/output channels to satisfy the storage and data movement demands of the computations targeted. Efficiently synchronized multiple-RVP configurations, that may be viewed as Variable-Very-Long-Instruction-Word (V2LIW) architectures, can be constructed and adapted to match the computational requirements of specific robotics computations. The use of the RVP is illustrated through a detailed example of the Jacobian computation, demonstrating good speedup over conventional microprocessors even with a single RVP. The RVP has been developed to be implementable on a single VLSI chip using a 1.2 μm CMOS technology, so that a single-board multiple-RVP system may be targeted for use on a mobile robot.
Unable to display preview. Download preview PDF.
- D.J. Kriegman, D.M. Siegel, S. Narasimhan, J.M. Hollerbach and G.E. Gerpheide, “Computational Architecture for the Utah/MIT Hand,” Proc. of the IEEE International Conference on Robotics and Automation, pp. 918–924, St. Louis, MO, March 1985.Google Scholar
- J.B. Chen, R.S. Fearing, B.S. Armstrong and J.W. Burdick, “NYMPH: A Multiprocessor for Manipulation Applications,” Proc. of the IEEE International Conference on Robotics and Automation. Vol. 3, pp. 1731–1736, San Francisco, CA, April 1986.Google Scholar
- R.B. McGhee, D.E. Orin, D.R. Pugh and M.R. Patterson, “A Hierarchically-Structured System for Computer Control of a Hexapod Walking Machine,” Proc. of Symposium on Theory and Practice of Robots and Manipulators. Udine, Italy, June 1984.Google Scholar
- J. Barhen, “Robot Inverse Dynamics on a Concurrent Computation Ensemble,” Proc. of 1985 ASME International Conference on Computers in Engineering. Vol. 3, pp. 415–429, Boston, MA, August 1985.Google Scholar
- D.E. Orin, K.W. Olson and H.H. Chao, “Systolic Architectures for Computation of the Jacobian for Robot Manipulators,” in Computer Architectures for Robotics and Automation, pp. 39–67, Edited by J.H. Graham, Gordon and Breach Science Publishers, New York, 1987.Google Scholar
- M. Amin-Javaheri and D.E. Orin, “A Systolic Architecture for Computation of the Manipulator Inertia Matrix,” Proc. of the IEEE International Conference on Robotics and Automation. Vol. 2, pp. 647–653, Raleigh, NC, April 1987.Google Scholar
- Y. Wang and S.E. Butner, “A New Architecture for Robot Control,” Proc. of the IEEE International Conference on Robotics and Automation. Vol. 2, pp. 664–670, Raleigh, NC, April 1987.Google Scholar
- H.H. Chao, Parallel/Pipeline VLSI Computing Structures for Robotics Applications. Ph. D. dissertation, The Ohio State University, Columbus, OH, June 1985.Google Scholar
- Y.L.C. Ling, K. Olson, D.E. Orin and P. Sadayappan, “A Layered Restructurable VLSI Architecture for Robotics Control,” Proc. of 1987 IEEE International Conference on Computer Design, pp. 267–272, Port Chester, NY, October 1987.Google Scholar
- K. W. Lilly and D.E. Orin, “Multiprocessor Implementation of Dynamic Control Schemes for Robot Manipulators,” Proceedings of 1986 ASME International Computers in Engineering Conference. Vol. 1, pp. 53–59, Chicago, IL, July 1986.Google Scholar
- J.A. Fisher, “Very Long Instruction Word Architectures and the ELI-512,” Proceedings of 10th Annual Symposium on Computer Architecture, pp. 140–150, Stockholm, Sweden, June 1983.Google Scholar
- Y.L.C. Ling, Layered Multiprocessor Architecture Design in VLSI for Real-Time Robotic Control. Ph. D. dissertation, The Ohio State University, Columbus, OH, Dec. 1986.Google Scholar